# How to integrate Higgsfield MCP with Hermes

```json
{
  "title": "How to integrate Higgsfield MCP with Hermes",
  "toolkit": "Higgsfield MCP",
  "toolkit_slug": "higgsfield_mcp",
  "framework": "Hermes",
  "framework_slug": "hermes-agent",
  "url": "https://composio.dev/toolkits/higgsfield_mcp/framework/hermes-agent",
  "markdown_url": "https://composio.dev/toolkits/higgsfield_mcp/framework/hermes-agent.md",
  "updated_at": "2026-09-04T05:34:27.843Z"
}
```

## Introduction

Hermes is a 24/7 autonomous agent that lives on your computer or server — it remembers what it learns and evolves as your usage grows.
This guide explains the easiest and most robust way to connect your Higgsfield account to Hermes. You can do this through either Composio Connect CLI or Composio Connect MCP. For personal use we recommend the CLI, but you won't go wrong with MCP either.

## Also integrate Higgsfield MCP with

- [ChatGPT Work](https://composio.dev/toolkits/higgsfield_mcp/framework/chatgpt)
- [Claude Cowork](https://composio.dev/toolkits/higgsfield_mcp/framework/claude-cowork)

## TL;DR

### What is Composio Connect?
Composio Connect is a consumer offering that lets anyone plug 1,500+ applications directly into their agent harness — including Hermes. It can:
- Search and load tools from relevant toolkits on-demand, reducing context usage.
- Chain multiple tools to accomplish complex workflows via a remote workbench, without excessive back-and-forth with the LLM.
- Manage app authentication end-to-end with zero manual overhead.

## Connect Higgsfield MCP to Hermes

### Integrating Higgsfield with Hermes
### Using Composio Connect CLI
1. Install the Composio CLI
Run the install script directly, or paste https://composio.dev/hermes into your Hermes chat box to have it installed for you.

```bash
curl -fsSL https://composio.dev/install | bash
```

## What is the Higgsfield MCP server, and what's possible with it?

The Higgsfield MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Higgsfield account. It provides structured and secure access so your agent can perform Higgsfield operations on your behalf.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `HIGGSFIELD_MCP_ANIMATION_ACTIONS` | Animation actions | Read-only catalog of the 3D rig animation library (678 actions: locomotion, gestures, dancing, combat, daily actions). Search by name or browse by group/category to find the animation_action_id for 3D generation with enable_animation=true. Each result has a preview_url GIF — when several candidates fit (e.g. many Idle or Walk variants), show the user the previews as markdown images and let them pick instead of choosing blindly. Does not create jobs. |
| `HIGGSFIELD_MCP_APPS_DESCRIBE` | Apps describe | Get an app's action contract: with `action`, the full input/output schema + execution mode for that one action; without it, a summary of every action. Also returns `manifest_revision`, which apps_invoke requires. Read-only. |
| `HIGGSFIELD_MCP_APPS_INVOKE` | Apps invoke | Run one described action on a Marketplace app AS the current user. First call apps_describe(app_id, action) to get the exact `arguments` schema and the `manifest_revision`, then pass them here. Long-running actions return { id, status: "queued" }. If a widget is visible, it polls the status action automatically — do not re-invoke get_* as a follow-up poll. In text-only clients, poll by invoking the app's status action (e.g. get_render) until status is completed/failed. The action's own annotations (from apps_describe) indicate cost/side-effects; confirm with the user before an expensive or destructive action. |
| `HIGGSFIELD_MCP_APPS_SEARCH` | Apps search | Search Higgsfield Marketplace apps callable through MCP. Returns each app's id, name, and the actions it exposes. Flow: apps_search to find an app → apps_describe(app_id, action) to get an action's argument schema + manifest_revision → apps_invoke to run it. Read-only; does not call any app. |
| `HIGGSFIELD_MCP_BALANCE` | Balance | Get the user's available credits and current subscription plan. For transaction history, call `transactions` instead. |
| `HIGGSFIELD_MCP_CANCEL_TRIAL_AUTO_RENEWAL` | Cancel trial auto renewal | Cancel the auto-renewal of the Higgsfield MCP free trial. Call this when the user asks to cancel the trial, cancel auto-renewal, stop the upcoming charge, or asks how to cancel. IMPORTANT SEMANTICS: cancelling stops the automatic charge at the end of the trial ONLY — the user KEEPS trial access and remaining trial credits until the trial ends; nothing is charged. First call WITHOUT `confirm` (or confirm=false): in UI clients this opens a confirmation card with 'Keep trial with auto-renewal' and 'Cancel auto-renewal' buttons; in text-only clients relay `assistant_response` verbatim and wait for the user's explicit confirmation. Only call again with `confirm=true` after the user explicitly confirmed the cancellation in chat. Never pass confirm=true on the first call. |
| `HIGGSFIELD_MCP_CONFIRM_BILLING_PURCHASE` | Confirm billing purchase | INTERNAL — invoked ONLY by the plans widget on an explicit user Confirm click. Do NOT call this tool yourself; it charges the user's real saved payment method off-session. To help a user upgrade, top up, or set auto top-up, call `show_plans_and_credits` instead — it returns checkout links and, in UI clients, opens the widget where the user confirms the charge. Covers auto_topup and topup via the `action` field (upgrade_plan is temporarily disabled — plan upgrades use the hosted checkout link). The backend either charges the saved card (`result: "charged"`) or returns a `checkout_url` to redirect (`result: "redirect"`). Buying a brand-new subscription is not handled here — that uses the hosted checkout link. |
| `HIGGSFIELD_MCP_CONFIRM_TRIAL_CANCEL` | Confirm trial cancel | INTERNAL — invoked ONLY by the cancel-trial confirmation widget on an explicit user click of 'Cancel auto-renewal'. Do NOT call this tool yourself; to cancel the trial's auto-renewal use `cancel_trial_auto_renewal` instead. Stops the trial's auto-renewal (cancel_at_period_end) — trial access and remaining credits stay until the trial ends. |
| `HIGGSFIELD_MCP_CREATE_VOICE` | Create voice | Open the Create Voice Apps UI. Call this immediately when the user asks to create a voice, call the Create Voice tool, or needs a local browser record/upload surface and no confirmed audio_media_id is already present. Do not ask the user to upload an audio file or provide the name in chat first; the widget collects the required name plus record/upload audio. If the user already has or attached an audio file in chat, still call this tool with initial_tab='upload' — remote tools cannot read Claude chat attachments, so the user re-selects the file in the widget's Upload tab (it uploads directly to Higgsfield). Do not try to pass a chat attachment or ask for a URL. The widget records/uploads, confirms the audio, and creates the voice itself end-to-end — and if the user is out of credits or on a free plan it shows the plans/credits UI inline. After the widget reports success you do NOT need to call create_voice_from_confirmed_audio again. Only call create_voice_from_confirmed_audio yourself when a confirmed audio_media_id is already present in the prompt and no UI step is needed. |
| `HIGGSFIELD_MCP_CREATE_VOICE_FROM_CONFIRMED_AUDIO` | Create voice from confirmed audio | Backend-only creation of a cloned voice from an already confirmed audio upload. Do not call this tool until audio_media_id and name are already known. For direct creation, first upload speech audio with media_upload, PUT the bytes, then call media_confirm with type='audio'. Pass that confirmed media_id here as audio_media_id plus a required name. If the user needs to record or upload local audio in an Apps UI-capable client, call create_voice instead; that widget records/uploads, confirms, and creates the voice itself, so you do not call this tool for the UI flow. The audio should be clear speech, roughly 10 seconds to 3 minutes, and no larger than the upload limit. The backend charges the voice-clone credit cost on successful creation. Cloning is asynchronous: on success the tool returns the new voice_id plus a status, and a fresh clone is usually still 'processing' and not yet usable. Use the returned voice_id with voice_type='element' for generate_audio or voice_change only once it is ready (status='completed' and is_audio_eligible=true). If status is 'processing' or is_audio_eligible is not true, the clone is still training — re-check it with list_voices before generating instead of submitting right away; status 'voice_clone_failed'/'failed' means cloning did not succeed. If recovery_tool is returned, call it immediately; do not explain/ask first. |
| `HIGGSFIELD_MCP_CREATE_WEBSITE` | Create website | Start a new full-stack website. Creates the website and a git repo: a React 19 + TanStack Start app, server-rendered, in ONE Cloudflare Worker, with D1 / R2 / KV / Durable Objects / Containers available (all DISABLED by default). Returns a website_id — pass it to every later website tool. The 'type' param is REQUIRED and is the USER'S choice, not yours: unless the user has already made it unambiguous, ASK the user whether they want a plain website (no Higgsfield integration) or a Higgsfield-integrated app (Sign in with Higgsfield + AI image/video generation via the Higgsfield SDK) BEFORE calling this tool. Apps are scaffolded from a v2 starter template and REQUIRE the 'template' param — pick the closest of studio / preset / app-detail per the template param's guide ('custom' is ONLY for when the user explicitly says "use custom template" — never pick it yourself). The chosen layout ships as real code already wired as the home page; you ADAPT IT IN PLACE, never rebuild it. Websites take an OPTIONAL template: pass 'scroll-scrub' for an animated website (its scrub engine ships pre-built) and omit it for a non-animated one. App and website templates are not interchangeable — a cross-kind name is rejected. Workflow: (0) call get_workflow_instructions with { workflow: "website-builder-flow" } FIRST to load the stack, design contract, and hard rules (REQUIRED before building or editing); (1) create_website; (2) call website_repo_access to get the repo's git URL + scoped token, clone/edit/commit/push with the terminal (for apps, read app/src/layouts/AGENTS.md + app/src/components/AGENTS.md right after cloning); (3) deploy_website to ship it live — and deploy again after ANY later change (publish_website only lists what is already live; it does not deploy). |
| `HIGGSFIELD_MCP_DEPLOY_WEBSITE` | Deploy website | Build and deploy the website via CI, then return its live URL. Every deploy ships the live site at the website's public URL (there is no separate preview stage). IMPORTANT: commit and git push ALL your changes BEFORE calling this — the build runs from the pushed repo. Deploy again after ANY later change: publish_website does NOT deploy (it only lists the already-live build on the community feed), so this tool is the only way changes ship. A failed build returns the log; a still-running build returns status 'pending' — call website_status to check. |
| `HIGGSFIELD_MCP_DUBBING` | Dubbing | Dub a video into another language: translate the spoken audio, synthesize it in the target language, and lip-sync the result back onto the video. Use this when the user asks to dub, translate the speech of, or localize a clip into another language. Pass video_id for the source video (a confirmed uploaded media_id or a completed video generation job_id) and target_language as one of the supported language codes. Supported languages (code=language): eng=English, cmn=Chinese, fra=French, hin=Hindi, ita=Italian, jpn=Japanese, kor=Korean, por=Portuguese, rus=Russian, tur=Turkish, spa=Spanish, deu=German, ara=Arabic, pol=Polish, ind=Indonesian, fil=Filipino, swe=Swedish, fin=Finnish. This tool does not use prompt or count; output dimensions are taken from the source video automatically. |
| `HIGGSFIELD_MCP_GENERATE_3D` | Generate 3d | Generate a 3D GLB mesh. Use `models_explore(type:'3d')` to pick a model and see its `medias[].roles` and `parameters`. Apps UI local file: call `media_upload_widget`; remote tools cannot read Claude chat attachments. Web media URL: call `media_import_url`, pass returned `media_id`; `medias[].value` must be media_id/job_id, not URL. Defaults: `image_to_3d` for general image-to-3D with optional texturing, PBR, and rigging; `multi_image_to_3d` when 2-4 views of the same subject are available (better geometric accuracy); `sam_3_3d` for single-object reconstruction; `3d_rigging` to rig an existing 3D model (takes `model_url`, not images — pass a prior 3D job_id or an https GLB URL). For animated rigs, search clip ids with the `animation_actions` tool and pass `animation_action_id` with `enable_animation:true`. The mesh reproduces only what is in the source image — to add or change props, clothing, or held objects, edit the image first with `generate_image`, then convert the edited result. Pass model-specific params as top-level fields. Apply `adjustments` returned by the server. If `recovery_tool` is returned, call it immediately. `get_cost:true` preflights credits without submitting. |
| `HIGGSFIELD_MCP_GENERATE_AUDIO` | Generate audio | Generate one speech/voice request (text-to-speech) and render it in the generation widget. This tool accepts one prompt; for 2-12 independent lines or prompts, use the headless generate_audio_batch tool instead. DEFAULT model: seed_audio (Seed Audio 1.0 by ByteDance) — use it unless the user explicitly asks for a different engine. seed_audio takes a preset or reference-element voice (voice_type 'preset'\|'element' + voice_id) plus optional tuning params (format, sample_rate, speech_rate, loudness_rate, pitch_rate), and can clone a voice from an audio_references media item or take an image_references cue. To use a specific named engine instead, set model:'text2speech_v2' and pass variant (one of elevenlabs\|minimax\|seed_speech\|vibe_voice\|cozy_voice) together with voice_type + voice_id. Get voice ids from list_voices; use models_explore(type:'audio') to inspect each model's params. This tool only generates speech: it cannot generate music or sound effects for general use, and there is no standalone music/SFX model here — decline general music or sound-effect requests rather than substituting a speech model. The models sonilo_music (music), mirelo_text_to_audio (sound effects) and inworld_text_to_speech (voice) exist ONLY for the game-generation pipeline and must not be used for standalone audio. get_cost:true preflights credits without submitting. use_unlim defaults false — pass true only when the user explicitly asks to use their unlimited/free-trial generations, never to save them credits on your own initiative. |
| `HIGGSFIELD_MCP_GENERATE_AUDIO_BATCH` | Generate audio batch | Submit 1-12 independent audio generations in parallel without opening a widget. Each requests[] item accepts the same params as generate_audio, creates exactly one job, and keeps its caller-provided index in the response. Use for multiple distinct prompts or inputs; use generate_audio for one user-facing generation. Poll returned job IDs with jobs_wait in agent-chosen groups of at most 12. For larger sets, collect indexed jobs across submission batches. After every job in the user's set is terminal, pass the collected jobs to exactly one show_generation_by_ids call for up to 60 jobs; never use show_generations or call job_display once per job. |
| `HIGGSFIELD_MCP_GENERATE_IMAGE` | Generate image | Generate one image request and render its result(s) in the generation widget. Use count 2-4 only for variants of the same prompt, inputs, and settings; for 2-12 independent image requests with different prompts or inputs, use the headless generate_image_batch tool instead. Apps UI local file media: call `media_upload_widget`; do not ask for Claude chat attachments because remote tools cannot read them. Web media URL: call `media_import_url`, then pass returned `media_id`; `medias[].value` must be media_id/job_id, not URL. Defaults: `marketing_studio_image` for commercial/product/ads; `soul_cast` for text-only character/avatar; `soul_2`+`soul_id` for trained reusable Soul; `soul_2`/`nano_banana_pro` for one-off character refs; `soul_2` for portraits/fashion/UGC/editorial; `nano_banana_pro` for 4K/text/diagrams. Ambiguous create-character/avatar: offer reusable Soul training (5-20 photos, ~10 min) vs one-off; do not train generic silently. Use `show_characters(action='train')` only if explicitly requested or user provides 5-20 photos. Use `models_explore` for aspect_ratios, params, medias roles. Top-level model params; apply `adjustments`. If `recovery_tool` returned, call it immediately; do not explain/ask first. `get_cost:true` preflights credits. `use_unlim` defaults false — pass true only when the user explicitly asks to use their unlimited/free-trial generations, never to save them credits on your own initiative. |
| `HIGGSFIELD_MCP_GENERATE_IMAGE_BATCH` | Generate image batch | Submit 1-12 independent image generations in parallel without opening a widget. Each requests[] item accepts the same params as generate_image, creates exactly one job, and keeps its caller-provided index in the response. Use for multiple distinct prompts or inputs; use generate_image for one user-facing generation. Poll returned job IDs with jobs_wait in agent-chosen groups of at most 12. For larger sets, collect indexed jobs across submission batches. After every job in the user's set is terminal, pass the collected jobs to exactly one show_generation_by_ids call for up to 60 jobs; never use show_generations or call job_display once per job. |
| `HIGGSFIELD_MCP_GENERATE_VIDEO` | Generate video | Generate one direct video request and render it in the generation widget. Use count 2-4 only for variants of the same prompt, inputs, and settings; use headless generate_video_batch for 2-12 independent requests. GENJUTSU TRIGGERS: route `Higgsfield Genjutsu` by intent. Copy, repeat, reproduce, mimic, or transfer motion, movement, actions, gestures, dance, or camera motion from one driving video to reference-image subjects -> `hf_mult_motion_control`. Replace, change, or swap an object, product, garment, or character in one source video from reference images -> `hf_mult_replace_object`. These are direct `generate_video` models, not legacy `motion_control` or `ad-multiplier`; reserve ad-multiplier for explicitly requested independent variants. Pass images with role `image` and exactly one source/driving video with role `video`. LOCAL/ATTACHED INPUT GATE: without confirmed media_id values, call `media_upload_widget` first as the only tool in that turn; never inspect /mnt/user-data/uploads, run shell, or ask for a chat attachment. For mixed image+video use type:`auto`, multiple:true. For web media call `media_import_url`; `medias[].value` must be media_id/job_id. Defaults: `marketing_studio_video` for ads/products, `clipify` for YouTube clips, `seedance_2_5` for general video, `kling3_0` for multi-shot, audio, or motion transfer, and `minimax_h3` for 2K keyframes or mixed references. Marketing Studio: fetch URL products with `show_marketing_studio(action='fetch')`; create uploaded-image products with type `product`. List missing hooks/settings before presets. Use declared media roles and model-supported audio only. Use models_explore for durations/params. Apply adjustments and immediately call any recovery_tool. get_cost:true preflights credits. Set use_unlim:true only when explicitly requested. |
| `HIGGSFIELD_MCP_GENERATE_VIDEO_BATCH` | Generate video batch | Submit 1-12 independent video generations in parallel without opening a widget. Each requests[] item accepts the same params as generate_video, creates exactly one job, and keeps its caller-provided index in the response. Use for multiple distinct prompts or inputs; use generate_video for one user-facing generation. Poll returned job IDs with jobs_wait in agent-chosen groups of at most 12. For larger sets, collect indexed jobs across submission batches. After every job in the user's set is terminal, pass the collected jobs to exactly one show_generation_by_ids call for up to 60 jobs; never use show_generations or call job_display once per job. |
| `HIGGSFIELD_MCP_GET_EXPLAINER_PRESETS` | Get explainer presets | Show the explainer video style presets (CMS-managed catalog). Returns preset ids, names, and preview media. When the user picks one, resolve it with resolve_explainer_preset to get the style reference media_id for generations. |
| `HIGGSFIELD_MCP_GET_WORKFLOW_BUNDLE_FILE` | Get workflow bundle file | Read a safe text file or directory from a workflow's resource folder. Use this after get_workflow_instructions when the SKILL.md requires a template, reference, or script file. |
| `HIGGSFIELD_MCP_GET_WORKFLOW_INSTRUCTIONS` | Get workflow instructions | Ad Multiplier — load workflow 'ad-multiplier' when the user asks to 'multiply my video', 'multiply my ad', create multiple independently edited versions of one supplied 4-30 second video, or regenerate the same ad with different people or products. Load this workflow before Marketing Studio, model browsing, or direct generation. Brand Asset Creation: for branded-asset work including logo recoloring/export, a branded PowerPoint/presentation deck, or analyzing an official brandbook to produce an asset, even when all inputs are supplied or no generation is needed, load 'brand-asset-creation' before sandbox_exec. Faceless video generation, AI-narrated video, narrated animated explainer video, narrated / personal / philosophical story video, YouTube/Instagram thumbnail or video cover, product photoshoot, packshot, studio or lifestyle product photography, product hero banner, product carousel, static product ad pack, virtual model product try-on, conceptual product still, or product-photo restyle, UGC-style ad for a website / SaaS / store / product page from its URL ('SaaS UGC'), any other UGC / creator-style short video for a product — a talking-head creator review (the default UGC ask), a product-only ad with no creator on camera, an unboxing / first-reaction / haul, a try-on / fit check / OOTD, a step-by-step tutorial with on-screen steps, a character sheet, character reference, model sheet, turnaround, expression sheet, or consistent multi-view character prompt, any branding work — a logo, visual identity, brand kit, brandbook, branded mockups, merchandise, packaging, signage, social graphics, posters, or banners ('brand-asset-creation'), including recoloring or exporting an existing official SVG/PNG logo even when no new design or image generation is requested, or building / editing a website, web app, landing page, or browser game with the website tools ('website-builder-flow'): before building ANY of these, use this tool to discover and load the bundled workflow (each a SKILL.md that orchestrates the generate_* tools). Call with NO argument to list available workflows and their triggers. Call with a workflow name to load that workflow's full SKILL.md plus the list of files readable via get_workflow_bundle_file. |
| `HIGGSFIELD_MCP_JOB_DISPLAY` | Job display | Show one specific previous generation in the single-result UI widget by job ID. Use when the user wants to inspect or re-display that individual result, including workflows that require separate approval of named candidates or individual previews before finalization. Do not call job_display once per job merely to reproduce an ordinary completed batch; use one show_generation_by_ids call for ordinary batch results instead. |
| `HIGGSFIELD_MCP_JOB_STATUS` | Job status | Check the status and results of an async job. Returns instantly. For non-terminal jobs the response includes poll_after_seconds — wait that many seconds before calling again. Typical total times: image ~10-20s, video ~60-180s. |
| `HIGGSFIELD_MCP_JOBS_WAIT` | Jobs wait | Long-poll 1-12 generation jobs together without opening a widget. Waits up to timeout_seconds (default 15, max 15) for every job to reach a terminal state, then returns compact indexed statuses and result URLs. Use job IDs returned by generate_image_batch, generate_video_batch, or generate_audio_batch. For larger sets, choose groups of at most 12 and wait for each group. Permanent lookup failures are returned once without blocking the other jobs; transient lookup failures are retried within the timeout. When all_terminal is false, wait poll_after_seconds before calling again. After every wait group in the user's generation set is terminal, collect their indexed jobs and display them with one show_generation_by_ids call when within that tool's limit. Never use show_generations or call job_display once per batch job. |
| `HIGGSFIELD_MCP_LIST_VOICES` | List voices | List available voices for speech and voice tools. Returns built-in preset voices plus the user's own custom voices. Each voice has a voice_id and a voice_type ('preset' or 'element'); pass that exact pair to the audio models (via generate_audio — seed_audio or text2speech_v2) and to the voice_change tool to select the speaking voice. Use the preview_url to hear a sample. Paginate with the returned next_cursor. |
| `HIGGSFIELD_MCP_LIST_WEBSITE_CATEGORIES` | List website categories | List the content categories a website can be filed under — each with a slug, label, description, and display position. create_website REQUIRES a `category`; call this first to get the valid slugs, then pass the closest one ('other' when nothing fits). |
| `HIGGSFIELD_MCP_LIST_WEBSITES` | List websites | List the websites you own — each with its id, name, slug, and live URL. Use this to find the id of a website you created earlier so you can edit, deploy, or check its status. |
| `HIGGSFIELD_MCP_LIST_WORKSPACES` | List workspaces | List every workspace the user can access (their private workspace plus any shared/team workspaces). The `is_selected` field marks which workspace MCP operations currently target. Use when the user asks which workspaces they have, or wants to switch workspace. |
| `HIGGSFIELD_MCP_MARKETING_STUDIO_V2_AVATARS` | Marketing studio v2 avatars | Widget-internal: list the user's Marketing Studio avatars (preset and custom) for the avatar picker. |
| `HIGGSFIELD_MCP_MARKETING_STUDIO_V2_COSTS` | Marketing studio v2 costs | Widget-internal: the Marketing Studio v2 pricing document. credits = cost_units / cost_units_per_credit; video flows cost fixed_cost_units + cost_units_per_second × duration. |
| `HIGGSFIELD_MCP_MARKETING_STUDIO_V2_CREATE` | Marketing studio v2 create | Widget-internal: recreate a Marketing Studio v2 preset — validates inputs against the preset's recreate contract and submits one generation. |
| `HIGGSFIELD_MCP_MARKETING_STUDIO_V2_PRESETS` | Marketing studio v2 presets | Widget-internal: load a page of the Marketing Studio v2 preset feed for a category. |
| `HIGGSFIELD_MCP_MARKETING_STUDIO_V2_STATUS` | Marketing studio v2 status | Widget-internal: poll status and results of submitted Marketing Studio v2 jobs. |
| `HIGGSFIELD_MCP_MEDIA_CONFIRM` | Media confirm | Confirm file uploads after using media_upload's upload_url method. Call this only after every curl PUT returned HTTP 200. Supports confirming multiple uploads at once via media_ids. |
| `HIGGSFIELD_MCP_MEDIA_IMPORT_URL` | Media import url | Import an HTTPS image, video, or audio URL into Higgsfield storage and return a confirmed media_id. Use this before generate_image/generate_video when the user provides a web media URL; generation medias should receive the returned media_id, not the original URL. Max URL payload: 50 MB. |
| `HIGGSFIELD_MCP_MEDIA_UPLOAD` | Media upload | Upload media for use in generation, or general files (documents, archives, code) for sharing. Returns presigned URLs for clients that can upload bytes themselves; run the generated curl commands or PUT the bytes to each upload_url, then call media_confirm. The media type is inferred from the filename extension: image/video/audio extensions become generation inputs; other whitelisted extensions (pdf, zip, tar, docx, csv, code files, …) are uploaded as general files and return a permanent URL, but cannot be used as generation inputs. General files are the agent's own upload path — the widget does not accept them, so upload the bytes to upload_url yourself (e.g. from a code execution environment). Supports batch uploads via files[]. Do not use this for user-provided local image/video/audio in Claude Apps UI-capable clients; call media_upload_widget instead so the user chooses the file in the Higgsfield widget and the browser uploads it directly. |
| `HIGGSFIELD_MCP_MEDIA_UPLOAD_WIDGET` | Media upload widget | Required local-media intake for Higgsfield in Apps UI-capable clients. Call this immediately as the only tool in the turn when the user refers to an attached/local photo, image, video, or audio but the prompt has no confirmed media_id yet. Do not inspect /mnt/user-data/uploads, run shell/sandbox commands, or ask the user to attach the file in Claude chat; remote MCP tools cannot read chat attachments. This widget is the upload surface: the user re-selects one or more files in the browser, the browser uploads them directly to Higgsfield storage, the widget confirms them, then sends the confirmed media_id/media_ids back to Claude for the next generation or analysis tool call. Use type auto with multiple enabled when one request needs mixed media, such as reference images plus a driving video; one video and one audio file may be combined with multiple images. The widget accepts media only; for general files (archives, documents, code) use media_upload instead and upload the bytes to the presigned upload_url yourself. |
| `HIGGSFIELD_MCP_MODELS_EXPLORE` | Models explore | Find generation models. Use recommend with goal + input context; use get for model constraints. Items carry supports_unlim when the model accepts free-trial unlimited generations; the top-level unlim block says whether the caller can spend them right now, and the trailing 'Unlim configs' text lists the configurations their allowance actually covers. |
| `HIGGSFIELD_MCP_MOTION_CONTROL` | Motion control | Animate an existing character image with the motion and camera movement from a reference video using Kling 3.0 Motion Control. Use this when the user asks to recast, puppeteer, transfer motion, or make a character follow a driving clip. Pass image_id for the character still and motion_video_id for the reference motion video; each can be a confirmed uploaded media_id or a completed generation job_id. This tool does not use prompt or count; the scene prompt and background setup are handled automatically. resolution controls output quality, and scene_control chooses whether the background is based on the image or the video. |
| `HIGGSFIELD_MCP_OUTPAINT_IMAGE` | Outpaint image | Expand or uncrop an existing image by outpainting beyond the original frame while preserving the source content. Use this when the user asks to extend the background, make an image wider or taller, change the canvas shape, or fill new edges around an image. Pass image_id for the source image and aspect_ratio for the target canvas. Optional width and height can be provided together; otherwise they default from aspect_ratio. This tool does not use prompt or count. Set params.get_cost=true to estimate credits without submitting a job. |
| `HIGGSFIELD_MCP_PARTICIPATE_IN_CONTEST` | Participate in contest | Enter the website in the current Higgsfield app contest, together with the social-media links promoting it. A website not yet PUBLISHED to the community feed is published automatically by the entry — no need to call publish_website first. The website DOES need a live production deploy (deploy_website), else the entry is rejected. BEFORE entering, make sure the page metadata in app/src/app-meta.json is filled with real values (og_title etc.) — the auto-publish lists the website on the feed and an empty og_title makes it INVISIBLE there. Pass one or more urls, each a social-media link (YouTube, X/Twitter, Instagram, or TikTok); any other host is rejected. There is a single active contest, so no contest id is needed. Calling again for the same website OVERWRITES its urls (use it to fix or add links), it does not create a second entry. |
| `HIGGSFIELD_MCP_PERSONAL_CLIPPER_CREATE` | Personal clipper create | Turn YouTube videos into ready-to-share clips. This is a long-running job and can take up to 30+ minutes. Before starting, ask the user how many clips they want, which clip aspect ratio to use, and which subtitle font they prefer. |
| `HIGGSFIELD_MCP_PERSONAL_CLIPPER_JOBS` | Personal clipper jobs | Show recent clipping jobs. |
| `HIGGSFIELD_MCP_PERSONAL_CLIPPER_STATUS` | Personal clipper status | Check clip creation progress. |
| `HIGGSFIELD_MCP_PRESETS_SHOW` | Presets show | Show available Higgsfield presets for image-to-video generation. Returns preset ids, names, previews, and descriptions. |
| `HIGGSFIELD_MCP_PUBLISH_WEBSITE` | Publish website | Publish the website: lists the website's CURRENT LIVE production deploy on the Higgsfield community feed ('show in feed'), where other users can discover it. This does NOT deploy — deploy_website (which every build flow already runs) must have shipped the latest changes first; publishing with undeployed changes lists the OLD live build, and re-publishing does not re-deploy. BEFORE publishing, the page metadata in app/src/app-meta.json MUST be filled with real values — og_title, og_description, favicon_url, og_image_url — the feed card renders from them (read fresh from the pushed repo at publish time) and a website with an empty og_title is INVISIBLE on the feed; the live page's own head tags are baked at build time, so deploy AFTER changing them. Also OFFER the user a cover video for the card (og_video_url) — ask their permission first (video generation costs credits), never generate it unprompted. Commit and git push the metadata (and all other changes), then deploy, BEFORE calling this. Publish when the user asks to publish / share / go live on the feed, OR when they opted in to publishing at the start of the build — in that case publish automatically once the site is deployed with its metadata filled, without waiting to be asked again. For a plain deploy without a feed listing use deploy_website instead. EXCEPTION: a website whose production was never deployed (or was taken down by unpublish) falls back to deploying first — that returns status 'pending' while CI runs and the website is listed automatically once the deploy succeeds (check with website_status). |
| `HIGGSFIELD_MCP_REFRAME` | Reframe | Expand or reframe an existing video to a new aspect ratio while preserving the source content. Use this when the user asks to make a video vertical, horizontal, square, wider, taller, or fill new edges around a video. Pass medias with exactly one source video and aspect_ratio for the target canvas. Optional image references can guide the filled area; optional start_image can pin the first frame when the user provides a first-frame anchor. For source videos over 15 seconds, pass duration_seconds and resolution and use only the source video. This tool does not use prompt or count. Set params.get_cost=true to estimate credits without submitting a job. |
| `HIGGSFIELD_MCP_REMOVE_BACKGROUND` | Remove background | Remove or cut out the background from an existing image or video. Use this when the user asks for background removal, a transparent background, an isolated subject, a clean cutout, or a subject-only asset. Pass media_id for the source media and media_type as image or video; the matching background remover is selected automatically. This tool does not use prompt, count, or style parameters. |
| `HIGGSFIELD_MCP_RENAME_WEBSITE` | Rename website | Rename the website's SUBDOMAIN (the slug in its public URL). The site is re-deployed under the new subdomain and the OLD subdomain STOPS WORKING — anyone holding the old URL must be given the new one. Storage (database, files, config) and the code repo are KEPT; only the public address changes. Runs a full re-deploy and can take a couple of minutes; returns once the site is live at the new URL. Fails if the new subdomain is already taken or reserved, or if a deploy is already in flight — pick another subdomain and retry. |
| `HIGGSFIELD_MCP_RESOLVE_EXPLAINER_PRESET` | Resolve explainer preset | Resolve a explainer video style preset (from get_explainer_presets) into a style reference media_id: the backend imports the preset's style image into the user's media storage. Pass the returned media_id as the style reference image in generation calls for every scene of the explainer. |
| `HIGGSFIELD_MCP_REVEAL_GENERATION` | Reveal generation | Confirm the user has rights to the content of an `ip_detected` generation and flip its status to `completed`. Backend accepts only seedance-family jobs (cs_3_0, seedance_2_0, ms_video, etc) and only while the job is still in `ip_detected` state. Returns the updated generation. Used by the job-list widget's Reveal button after the user accepts the rights confirmation modal. |
| `HIGGSFIELD_MCP_SANDBOX_EXEC` | Sandbox exec | Execute a shell command in a remote Higgsfield cloud Linux sandbox — NOT your local machine or the client's own shell. Whenever a task needs shell tooling (ffmpeg, image/file conversion, scripting), use this tool, never a built-in or local bash/shell tool: only this sandbox has the media toolchain preinstalled and can reach the user's Higgsfield media. Preinstalled: ffmpeg/ffprobe, ImageMagick, sox, python3 with Pillow and faster-whisper, node/npm/npx, sharp-cli, Playwright with headless Chromium, caption fonts (Metropolis, Montserrat), zip/unzip, git, curl, jq. Use it for media processing (trim, convert, overlay, concat with ffmpeg), image manipulation, file conversion, scripting, and packaging that dedicated tools don't cover. The sandbox is isolated per user and is discarded ~10 seconds after a call finishes, so files in /home/user only survive between back-to-back calls — chain multi-step work into a single command (&&) and export results before finishing, or expect to re-download inputs. It has internet access: bring files in with curl from media URLs (media_import_url or generation results). For an output created here, call media_upload BEFORE starting the producing command, then append `curl -f -X PUT --upload-file ''` to that SAME command so the ephemeral file is uploaded before it exits; call media_confirm only after HTTP 200. Never pass a sandbox path to media_upload_and_confirm: that tool accepts only client attachments. Commands run in /home/user and time out after timeout_seconds (default 60, max 120); for longer work (large renders, installs) set background:true and poll the returned log/status files with later sandbox_exec calls. Background work receives a 15-minute sandbox lease, and shorter poll calls never reduce its remaining lifetime. Set restart:true to discard the sandbox and start clean. Workflow bundle scripts are already installed in every sandbox under $HF_WORKFLOWS (/home/user/.higgsfield/workflows), laid out as $HF_WORKFLOWS//scripts/... — run them straight from there (they survive restart:true), and never paste script contents into the command. |
| `HIGGSFIELD_MCP_SELECT_WORKSPACE` | Select workspace | Set or clear the active workspace — the one all subsequent MCP operations bill against and read from (generations, balance, transactions, uploads, custom references). How to work with workspaces: (1) call `list_workspaces` first to see the user's workspaces with their `id`, plan, available credits, and which one is currently active (`is_selected`); (2) call `select_workspace` with the chosen `workspace_id` to switch — e.g. to run and bill work under a shared/team workspace instead of the private default; (3) call again with `clear: true` to return to the default private workspace. The selection persists across sessions and clients until changed or cleared, so it stays in effect for later turns without re-selecting. When the user belongs to more than one workspace, confirm which one to use before billable operations. Returns an error if the workspace doesn't exist or the user isn't a member. |
| `HIGGSFIELD_MCP_SHORTS_STUDIO_CREATE` | Shorts studio create | Start a Shorts Studio short: restyle one uploaded source video (4s–120s) into a set of AI-generated short-form clips using a style preset. PAID — reserves credits. Prerequisites, gathered in whatever order fits the conversation: (1) a style preset — pick one via shorts_studio_list_presets or make one with shorts_studio_create_preset; (2) a source video — an uploaded video_input id from media_upload_widget (type=video). If the user hasn't provided a source video yet, ask them to upload one before calling this. Output orientation defaults to 9:16 (vertical); pass aspect_ratio:'16:9' for horizontal. Returns a session with empty job_ids; poll shorts_studio_status until clips appear. Set get_cost=true with duration_seconds to estimate the credit cost without submitting a job — no preset or source video needed for the estimate. |
| `HIGGSFIELD_MCP_SHORTS_STUDIO_CREATE_PRESET` | Shorts studio create preset | Create a user-owned Shorts Studio style preset from reference media (videos + images). This just stores a STYLE — no generation, no credits. Reference media must be public https URLs (use an uploaded media's url or media_import_url first). Limits: ≤10 media total, each video's duration ≤30s (send `duration` so the cap applies). Returns the id and preset_source to feed into shorts_studio_create. If the user did not give a name, invent a random friendly two-word name yourself (e.g. 'Amber Drift', 'Neon Tide', 'Velvet Dusk') — never leave it blank or ask. |
| `HIGGSFIELD_MCP_SHORTS_STUDIO_LIST_PRESETS` | Shorts studio list presets | Browse Shorts Studio style presets — the visual STYLE a short is restyled toward. Use this when the user wants to make a short and needs to choose a look: they can pick one of these or create their own style with shorts_studio_create_preset. Returns the user's own presets first, then the CMS library; each item carries a `preset_source` to pass straight into shorts_studio_create. Paginated: if next_cursor is not null, pass it as cursor to get the next page. |
| `HIGGSFIELD_MCP_SHORTS_STUDIO_LIST_SESSIONS` | Shorts studio list sessions | List the caller's past Shorts Studio sessions (newest first) to find a session_id to poll with shorts_studio_status. |
| `HIGGSFIELD_MCP_SHORTS_STUDIO_STATUS` | Shorts studio status | Poll one Shorts Studio session. Returns {id, status, job_ids}. status='completed' means every clip job is terminal (not necessarily successful). Poll each job_id via job_status for its clip video url and per-clip status. |
| `HIGGSFIELD_MCP_SHOW_CHARACTERS` | Show characters | Soul Characters widget — reusable trained identity models. Actions: `list` (browse), `train` (needs `name` + 5-20 ref images, ~10 min, non-blocking — widget polls), `status` (inspect by `soul_id`). Presence of `name`/`images`/`medias` ⇒ train mode. Call `train` only on explicit ask for a reusable Soul / digital twin / identity, or when 5+ ref photos are supplied. Ref images accept: media_id UUIDs from media_confirm, completed image-job IDs, or https URLs. Never local paths — upload via media_upload → PUT bytes → media_confirm first. CONSTRAINTS: - Trained Soul is usable ONLY with `soul_2` (Soul V2) and `soul_cinematic` (Soul Cinema). For any other model, the user needs `show_reference_elements`. - ONE soul_id per generation. Multi-character shots ('me + friend', 'two people') must use `show_reference_elements` (supports multiple `>>` placeholders). AMBIGUITY GUARD — character/avatar/digital-twin/'use my face' requests without a chosen path: do NOT call this tool yet; ask the user to pick: 1. Train Soul (this tool) — identity-faithful, ONE person, 5-20 photos, ~10 min, Soul V2 / Cinema only. 2. Save as Element (`show_reference_elements` action=create) — instant, single image, multiple subjects allowed, works with Nano Banana Pro / 2, GPT Image 2, Seedream 4.5 / 5 lite, Cinema Studio Image 2.5, Cinema Studio Video 2 / 3.0, Seedance 2.0, Kling 3.0. → Soul signals: 'train' / 'digital twin' / 'identity' / 5+ photos of same person. → Force Elements: >1 character in shot, non-person subject, single image, mention of a non-Soul model, instant result wanted. After ready: `generate_image` with `model: 'soul_2'` (or `soul_cinematic`) + the returned `soul_id`. |
| `HIGGSFIELD_MCP_SHOW_GENERATION_BY_IDS` | Show generation by ids | Render exactly 1-60 requested generation jobs in the full-profile gallery widget, ordered by index and paginated locally in groups of 12. Use once every jobs_wait group is terminal for generate_image_batch, generate_video_batch, or generate_audio_batch. Pass the complete indexed set collected from the batch tools. This tool fetches only those job IDs in bounded groups: it never loads generation history, uses cursors, requests additional pages, or adds other jobs. Do not use show_generations or job_display to present a completed batch. |
| `HIGGSFIELD_MCP_SHOW_GENERATIONS` | Show generations | Browse completed non-Marketing Studio generation history and render one paginated page in the gallery widget. Returns generations with {id, type, status, model, params, results}. Use only when the user explicitly asks to browse regular generation history. Do not use this history tool after generate_*_batch or jobs_wait; show an exact completed batch with one show_generation_by_ids call instead. Use show_marketing_studio_generations for Marketing Studio video/image/ad history. Pass a prior generation's id as value in the medias array of a new generation to reuse it. Use job_display only to inspect one specific previous result. Paginated: if next_cursor is not null, pass it as cursor to get the next page. |
| `HIGGSFIELD_MCP_SHOW_MARKETING_STUDIO_GENERATIONS` | Show marketing studio generations | Browse past completed Marketing Studio generations only. Returns Marketing Studio video and ad/image generations with {id, type, status, model, params, results}. Use show_generations for non-Marketing Studio image/video history. |
| `HIGGSFIELD_MCP_SHOW_MARKETING_STUDIO_V2` | Show marketing studio v2 | Open Marketing Studio — a template gallery widget with category tabs (UGC ads, product shots, motion graphics, posters, ads, marketplace) and a preset grid the user browses and recreates from with their own product image. Use this whenever the user asks for Marketing Studio or wants marketing assets from a template/preset catalog. The widget handles preset selection, inputs, generation, and result display itself — no follow-up tool calls needed. |
| `HIGGSFIELD_MCP_SHOW_MEDIAS` | Show medias | List your uploaded media files by type. Returns media IDs, URLs, and creation timestamps. Call once with the single type the user asked for (default image); do not enumerate the other types unless the user explicitly asks for them. Pass media IDs as value in the medias array of generation tools. Paginated: if next_cursor is not null, pass it as cursor to get the next page. |
| `HIGGSFIELD_MCP_SHOW_PLANS_AND_CREDITS` | Show plans and credits | Open the single combined pricing widget for everything billing-related. The widget has two tabs the user can switch between: **Upgrade Plan** (Plus + Ultra, monthly + annual subscription cards) and **Top-up Credits** (one-time credit packs of 500 / 1,000 / 2,000 / 4,000 credits). Cards include feature lists, 7-Day Unlimited highlights, and 365-Day Unlimited blocks pulled from the live pricing config. Each plan card and credit pack has a CTA that links directly to the relevant Stripe or Higgsfield checkout/setup URL — no separate tool is needed to mint checkouts. For every billing request, the text response and `assistant_response` are intentionally short, user-facing sales copy with checkout URLs wrapped as action-specific Markdown links such as `[Go to Checkout](url)`, `[Higgsfield Upgrade](url)`, `[Higgsfield Credit Top-up](url)`, `[Higgsfield Auto-refill](url)`, `[Higgsfield Team Top-up](url)`, or `[Higgsfield Team Auto-refill](url)`; relay that response verbatim instead of summarizing, saying only that the widget opened, or listing options without links. If the user asks to buy credits or they are out of credits, first push auto-refill when `auto_refill_purchase_link` is present, then show `credit_purchase_links`. If the user asks to upgrade or a minimum plan is required, show `plan_purchase_links`. Pass `intent='auto_refill'` for out-of-credits recovery, `intent='topup'` for one-time credit packs, `intent='upgrade'` for plan upgrades, or `intent='trial'` when the user specifically asks for the free trial so the response is ordered for that purchase path. FREE TRIAL: when `free_trial` is present in the response, the user is eligible for a 3-day $0 Plus trial with MCP-only credits — the widget shows it and the text response leads with it. In text-only clients ALWAYS relay `free_trial.compliance_note` verbatim (MCP-only, card required, automatic charge after the trial unless cancelled, how to cancel by saying 'cancel auto-renewal'). When `free_trial` is absent, NEVER speculate about trial eligibility or mention fraud/abuse checks — present the paid plans neutrally. When `initial_view='trial_upgrade'`, the user's trial credits are exhausted: relay the numbered upgrade options plus the renewal reminder, and mention that saying 'cancel auto-renewal' stops the upcoming charge while keeping trial access. To cancel the trial's auto-renewal, call `cancel_trial_auto_renewal` instead of this tool. Use this tool for ANY of these requests: plans, pricing, subscriptions, upgrade options, comparing tiers, buying credits, topping up credits, refilling credits, credit packs. Do not look for separate `show_plans` or `show_credit_topups` tools — both have been merged into this one. Returns `already_subscribed: true` when the workspace is already on a paid plan; the widget hides the Upgrade tab in that case and shows only credit top-ups. Team-plan workspaces: `workspace_kind` field indicates the context. When `workspace_kind='team_owner'`, the widget renders team-specific Top-up and Auto-refill UIs and emits `team_purchase_links` (two links: `team_top_up` and `team_auto_refill`) that deeplink to the team billing modals on higgsfield.ai — relay both Markdown links in the text response. When `workspace_kind='team_member'`, no purchase links are returned; the widget shows a read-only notice and the text response tells the user only the workspace owner can buy credits or change auto-refill. Do not invent purchase links for members. |
| `HIGGSFIELD_MCP_SHOW_REFERENCE_ELEMENTS` | Show reference elements | Elements widget — reusable characters / environments / props per workspace. Actions: - `list` (default; paginated by `created_at` DESC, use `cursor` from prev `next_cursor`). - `get` (default when `element_id` is set). - `create`: pass `medias[]` as `{ id, url, type: 'media_input' \| 'image_job' }`. Upload first via media_upload → PUT bytes → media_confirm. `category='auto'` lets the server classify (use explicit only on user ask). Omit `name` to auto-derive (per-workspace unique, collisions get a numeric suffix). Returns synchronously. AMBIGUITY GUARD vs Soul — user wants a reusable face of one specific person (digital twin / 'my avatar' / identity) without a chosen path: do NOT silently create; ask: 1. Element (this tool action=create) — instant, single image, MULTIPLE references per generation, works with Nano Banana Pro / 2, GPT Image 2, Seedream 4.5 / 5 lite, Cinema Studio Image 2.5, Cinema Studio Video 2 / 3.0, Seedance 2.0, Kling 3.0. NOT for Soul V2 / Cinema. 2. Soul (`show_characters` action=train) — 5-20 photos, ~10 min, ONE person, Soul V2 / Cinema only. Skip the question → Elements on: >1 character/subject in one shot (Soul can't), non-person subject, single image, mention of Nano Banana / Seedream / Kling / Cinema Studio, instant result. Skip → Soul on: 'train' / 'digital twin' / 'identity', or 5+ photos of one person for solo outputs. USAGE IN GENERATION (internal — never explain to user): Embed `>>` inside `params.prompt` of `generate_image` / `generate_video`. Backend auto-injects the image and rewrites to `@element_name`. Multiple placeholders per prompt OK. Example: `"Cinematic portrait of >> on a rooftop"`, `">> handing coffee to >> in a Paris cafe"`. SUPPORTED MODELS (`params.model` = machine name, friendly in parens): - Image: `nano_banana_pro` (Nano Banana Pro), `nano_banana_2` (Nano Banana 2), `gpt_image_2` (GPT Image 2), `seedream_v4_5` (Seedream 4.5), `seedream_v5_lite` (Seedream 5.0 lite), `cinematic_studio_2_5` (Cinema Studio Image 2.5). - Video: `cinematic_studio_video_v2` (Cinema Studio Video 2), `cinematic_studio_3_0` (Cinema Studio Video 3.0), `seedance_2_0` (Seedance 2.0), `kling3_0` (Kling 3.0 — REQUIRES a `start_image` in `params.medias`; element placeholder alone won't trigger reference usage). Map friendly→machine silently. Other models silently ignore the placeholder. USER-FACING STYLE: use friendly model names only; never expose machine names, `>>` syntax, `params.model` / `params.prompt`, `generate_image` / `generate_video`, or 'job_set_type'. Reference elements by `name`, never id. GUARDS: - `@name` form does NOT work in tool calls — only `>>` in `params.prompt`. - Do NOT put element ids in `params.medias` / `params.input_images` — placeholder handles injection. - `kling3_0` only honors reference elements when an explicit `start_image` is provided in `params.medias`. If the user wants Kling 3.0 with an element but hasn't supplied a start frame, ask for one (upload via media_upload → PUT bytes → media_confirm, or pick a prior generation) before calling `generate_video`. Without a start_image, pick another video model from the list. - Only `status: completed` elements are usable; skip `processing` / `ip_checking` / `failed` / `kling_failed` / `nsfw`. |
| `HIGGSFIELD_MCP_SYNC_AGENTS` | Sync agents | Sync Agents — imports the user's user-authored Skills and a personality dump from the current host LLM into Higgsfield. One trigger, one upload, one final confirmation. Calling modes: 1. `message: "/sync-agents"` — server returns a short ack in `content[0].text` plus an assistant-only directive containing a self-contained Python upload script (pre-wired with a one-time presigned POST URL scoped to one per-user prefix). Print the ack verbatim. Then follow the directive: enumerate user-authored skills + synthesize `personality.md` into `/tmp/profile-import/{skills,personality}/`, run the script in your code-execution sandbox, capture its single-line JSON summary, and call this tool again with that summary as `message`. 2. `message: ""` — server reads the uploaded .md files, parses each, and upserts the user's Skill rows. Returns a one-line confirmation summarising counts (e.g. "Imported 3 skill(s) (2 new, 1 updated) · personality queued for save to your memory."). Print that confirmation verbatim to the user. **Also pass `host`** on this call — your own runtime identifier (e.g. `claude_ai`, `claude_code`, `codex`, `cursor`); it is stamped on every newly imported skill's `import_origin` so the marketplace can attribute origin per host. No polling, no chains. Each call returns synchronously. |
| `HIGGSFIELD_MCP_TIKTOK_ACCOUNTS` | Tiktok accounts | List the user's connected TikTok accounts. Returns each account's connector_id (needed by other tiktok_* tools) and status. `active` accounts are ready; `error` accounts need tiktok_reconnect; no accounts ⇒ offer tiktok_connect. Read-only. |
| `HIGGSFIELD_MCP_TIKTOK_CONNECT` | Tiktok connect | Start connecting the user's TikTok account. Returns an authorize_url — show it to the user as a link; they open it in a browser, approve access on TikTok, and land on a confirmation page. Afterwards call tiktok_accounts to verify the account became `active`. The URL expires in ~10 minutes. If an account already exists in `error` status, use tiktok_reconnect instead. |
| `HIGGSFIELD_MCP_TIKTOK_MUSIC_TRENDING` | Tiktok music trending | List trending commercially licensed tracks from TikTok's Commercial Music Library for the connected account. Show the user a few tracks with their listen links and let them pick; then pass the chosen track's id as music_sound_id to tiktok_publish. Music works for DIRECT_POST only (TikTok drafts don't keep it). There is no keyword search — offer genre/country/date_range filters instead. Read-only. |
| `HIGGSFIELD_MCP_TIKTOK_MUSIC_TUNE` | Tiktok music tune | Open the tuning editor for one Commercial Music Library track the user already picked (via tiktok_music_trending): trim start/end and set track/original volumes. Pass the same genre/country_code/date_range filters that were used when the track was found, or the lookup may miss. The user copies the final configuration from the editor and pastes it into the chat; pass those values to tiktok_publish. Read-only. |
| `HIGGSFIELD_MCP_TIKTOK_PREPARE_PUBLISH` | Tiktok prepare publish | Step 1 of publishing to TikTok. Validates the media and TikTok account, creates a publish session, and returns what the user must review and choose (preview, privacy options, required declarations, confirmations). The media URL must be a Higgsfield-hosted asset (TikTok requires a verified source domain). Then collect the user's choices and call tiktok_publish. mode=DIRECT_POST posts to the profile; mode=UPLOAD_TO_DRAFT saves to the user's TikTok drafts. MEDIA LIMITS — check before calling, and convert or downscale locally if a file does not comply; a rejected file costs a full convert-and-re-upload round trip, and TikTok rejects some files only asynchronously, after the post was submitted. Photos: JPEG or WebP only (PNG is rejected by TikTok, and Higgsfield image generation emits PNG — convert first), each at most 20 MB, resolution must fit within 1920x1080 or 1080x1920, up to 35 images. Videos: MP4, WebM or MOV, at most 1 GB, 3-600 seconds, at least 360 px on both sides, 23-60 FPS. |
| `HIGGSFIELD_MCP_TIKTOK_PUBLISH` | Tiktok publish | Step 2 of publishing. Call only after tiktok_prepare_publish and after collecting the user's explicit choices and confirmations. Pass the publish_session_id from prepare (the media is locked to it — do not resend URLs). Set every flag listed in the prepare response's required_confirmations to true; these represent real user consent (AIGC/branded-content/music/privacy). Optionally attach a commercial track via music_sound_id from tiktok_music_trending (DIRECT_POST only). Returns a publish_id for tiktok_publish_status. PUBLISH QUOTAS per account, enforced before TikTok is called: at most 5 posts per minute and 13 posts per 24 hours, both rolling (TikTok's own ceiling is 6/minute and 15/day). A rejection returns code=cadence_burst or cadence_daily plus retry_after_seconds — wait that long instead of retrying, since retrying sooner only earns another rejection. Failed attempts and drafts do not consume quota; a post TikTok accepted does. Duration, frame size and frame rate are measured from the media file itself by tiktok_prepare_publish, before a publish slot is spent — there is no duration argument, never ask the user for one. music_sound_volume, video_original_sound_volume, music_sound_start and music_sound_end apply only together with music_sound_id and only to videos; without a track, or on a photo post, they are ignored. MEDIA LIMITS — check before calling, and convert or downscale locally if a file does not comply; a rejected file costs a full convert-and-re-upload round trip, and TikTok rejects some files only asynchronously, after the post was submitted. Photos: JPEG or WebP only (PNG is rejected by TikTok, and Higgsfield image generation emits PNG — convert first), each at most 20 MB, resolution must fit within 1920x1080 or 1080x1920, up to 35 images. Videos: MP4, WebM or MOV, at most 1 GB, 3-600 seconds, at least 360 px on both sides, 23-60 FPS. |
| `HIGGSFIELD_MCP_TIKTOK_PUBLISH_STATUS` | Tiktok publish status | Step 3 of publishing. Fetch processing status for a publish_id returned by tiktok_publish. TikTok may take a few minutes to process before the post is live. Read-only. |
| `HIGGSFIELD_MCP_TIKTOK_RECONNECT` | Tiktok reconnect | Re-run the TikTok OAuth for an existing connector in `error` status (expired/revoked access). Returns a fresh authorize_url — show it to the user as a link, then verify with tiktok_accounts. |
| `HIGGSFIELD_MCP_TRANSACTIONS` | Transactions | List the user's credit transactions (spend/refund/grant/deduct), newest first. Paginated: if next_cursor is not null, pass it as cursor to get the next page. |
| `HIGGSFIELD_MCP_UPSCALE_IMAGE` | Upscale image | Upscale and enhance an existing image. Use this when the user asks to upscale, enhance, or increase the resolution of an image to 2K/4K. This tool does not use prompt or count. Provider selects the upscale backend; currently only 'bytedance' is supported (the default). You MUST pass the source image's width and height in pixels (the caller supplies them; the server does not infer them). Set params.get_cost=true to preflight credits (flat cost) without submitting a job. |
| `HIGGSFIELD_MCP_UPSCALE_VIDEO` | Upscale video | Upscale and enhance an existing video. Use this when the user asks to upscale, enhance, sharpen, denoise, restore, or convert a video to higher resolution. This tool does not use prompt or count, and does not support cost preflight. Choose a provider: 'bytedance' (preset-based, target 1080p/2K/4K — you MUST pass the source video width/height in pixels and may set fps to 24/30/60) or 'topaz' (Topaz Video, aspect-ratio based, target 1080p/2160p — no source dimensions needed). |
| `HIGGSFIELD_MCP_VIDEO_ANALYSIS_CREATE` | Video analysis create | Start a scene-by-scene analysis of a video. Provide EXACTLY ONE of: (a) video_input_id — UUID of a video the user has uploaded via media_upload/media_confirm, or (b) youtube_url — a YouTube link (youtube.com / youtu.be hosts only). Returns immediately with status='queued'; poll video_analysis_status until status='completed'. Processing typically takes 3-5 minutes on average. IMPORTANT: warn the user up front that the longer the video, the less accurate the scene-by-scene analysis becomes — short clips give the most reliable results. |
| `HIGGSFIELD_MCP_VIDEO_ANALYSIS_JOBS` | Video analysis jobs | List the user's video analyses in the current workspace, newest first. Paginate by passing the previous response's cursor. |
| `HIGGSFIELD_MCP_VIDEO_ANALYSIS_STATUS` | Video analysis status | Get the status and result of a video analysis. Poll this after video_analysis_create until status='completed' (scenes populated) or 'failed' (fail_reason populated). Analyses typically finish in 3-5 minutes — poll accordingly every 30-60 seconds. |
| `HIGGSFIELD_MCP_VIRALITY_PREDICTOR` | Virality predictor | Virality Predictor predicts a video's virality potential, engagement, attention, audience response, retention risk, hook strength, and creative performance with an interactive dashboard. Use when the user asks whether a video can go viral or wants creative-performance analysis. Create starts analysis from a confirmed uploaded video or completed generated video; preview re-opens an existing dashboard. |
| `HIGGSFIELD_MCP_VOICE_CHANGE` | Voice change | Replace the spoken voice in a video with a different voice while keeping the original timing and visuals, then re-merge the new audio onto the video. Use this when the user asks to change, swap, or revoice the speaker in a clip. Pass video_id for the source video (a confirmed uploaded media_id or a completed video generation job_id) and voice_id for the target voice. voice_type selects whether voice_id is a built-in preset voice ('preset') or a workspace reference element ('element'). This tool does not use prompt or count; output dimensions are taken from the source video automatically. |
| `HIGGSFIELD_MCP_WEBSITE_DB` | Website db | Inspect the website's database (D1 / SQLite), READ-ONLY. The website has ONE database — the live site's real data. Pick an operation: 'tables' (list tables); 'schema' (a table's columns — needs table); 'rows' (a page of rows — needs table; optional filters, order_by + order_dir, limit (default 50) + offset); 'query' (one read-only SELECT/WITH — needs sql). Writes and DDL are rejected. |
| `HIGGSFIELD_MCP_WEBSITE_REPO_ACCESS` | Website repo access | Get direct git access to a website's repo to edit it — THE way to get the website's code. Returns the repo URL, branch, slug, and a scoped token; clone it with the terminal tool, edit files, commit + push, then call deploy_website. Clone into a directory named after the slug so multiple websites can share the workspace. Access is scoped to your own websites — do not echo the token back to the user. |
| `HIGGSFIELD_MCP_WEBSITE_SECRETS` | Website secrets | Manage a website's SECRETS (environment variables: API keys, tokens). Set them HERE instead of hardcoding them in source. One tool, three operations: 'set' (store/replace — needs name + value); 'delete' (remove — needs name); 'list' (the configured secrets as a {name: value} map). A change (set OR delete) is STAGED — NOT live until the next deploy_website. Read a secret SERVER-side in website code; never ship it to the browser. |
| `HIGGSFIELD_MCP_WEBSITE_STATUS` | Website status | Get the website's deploy status — the live URL and the status of the last deploy. Use to check a deploy that returned 'pending', or to fetch the live URL. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Higgsfield MCP server provides comprehensive access to Higgsfield operations through Composio. Once connected, Hermes can perform all major Higgsfield actions on your behalf using natural language commands.

## Complete Code

None listed.

## Conclusion

### Way Forward
With Higgsfield connected, Hermes can now act on your behalf whenever it detects a relevant task or you ask it to.
From here, you can extend Hermes further:
- Connect more apps: Calendar, Slack, Notion, Linear, and hundreds of others are available through the same Composio Connect setup. Each new integration compounds what Hermes can do for you.
- Build workflows across tools: Once multiple apps are connected, Hermes can chain actions together — turn an email into a calendar invite, a Slack message into a Linear ticket, or a meeting note into a follow-up draft.
- Let it learn your patterns: The more you use Hermes, the better it gets at anticipating how you'd handle recurring tasks. Give it feedback on drafts and decisions, and it will adapt.
If you run into trouble or want to share what you've built, join the [community](https://discord.com/invite/composio) or check out the [Docs](https://docs.composio.dev?utm_source=toolkits&utm_medium=framework_template&utm_campaign=hermes&utm_content=docs) for deeper configuration options.

## How to build Higgsfield MCP Agent with another framework

- [ChatGPT Work](https://composio.dev/toolkits/higgsfield_mcp/framework/chatgpt)
- [Claude Cowork](https://composio.dev/toolkits/higgsfield_mcp/framework/claude-cowork)

## Related Toolkits

- [Figma](https://composio.dev/toolkits/figma) - Figma is a collaborative interface design tool for teams and individuals. It streamlines design workflows with real-time collaboration and easy sharing.
- [Abyssale](https://composio.dev/toolkits/abyssale) - Abyssale is a creative automation platform for generating images, videos, GIFs, PDFs, and HTML5 content programmatically. It streamlines and scales visual content production for marketing, design, and operations teams.
- [Alttext ai](https://composio.dev/toolkits/alttext_ai) - AltText.ai is a service that generates alt text for images automatically. It helps boost accessibility and SEO for your visual content.
- [Are.na](https://composio.dev/toolkits/arena) - Are.na is a creative research platform for collecting images, links, notes, and ideas in channels. Use it to organize inspiration, build knowledge maps, and connect research across projects.
- [Bannerbear](https://composio.dev/toolkits/bannerbear) - Bannerbear is an API-driven platform for generating images and videos automatically at scale. It helps businesses create custom graphics, social visuals, and marketing assets using powerful templates.
- [Bannerbite](https://composio.dev/toolkits/bannerbite) - Bannerbite is a creative automation platform for generating images and videos from reusable projects and templates. It helps teams produce on-brand visual assets faster without rebuilding designs from scratch.
- [Builder.io](https://composio.dev/toolkits/builder_io) - Builder.io is a visual development platform for managing content, models, assets, and Space configuration. Use it to ship editable digital experiences faster without waiting on every code change.
- [Canva](https://composio.dev/toolkits/canva) - Canva is a drag-and-drop design suite for creating professional graphics, presentations, and marketing materials. It makes it easy for anyone to design with beautiful templates and a vast library of elements.
- [Canva MCP](https://composio.dev/toolkits/canva_mcp) - Canva MCP is Canva's remote MCP server for accessing designs and content. It centralizes design assets and enables programmatic design workflows.
- [Claid ai](https://composio.dev/toolkits/claid_ai) - Claid.ai delivers AI-driven image editing APIs for tasks like background removal, upscaling, and color correction. It helps automate and enhance image workflows with powerful, developer-friendly tools.
- [Cloudinary](https://composio.dev/toolkits/cloudinary) - Cloudinary is a cloud-based platform for managing, uploading, and transforming images and videos. It streamlines media workflows and delivers optimized assets globally.
- [Contentdrips](https://composio.dev/toolkits/contentdrips) - Contentdrips is an asynchronous rendering API for branded graphics and carousels. It turns reusable templates into on-brand social visuals at scale.
- [Creatomate](https://composio.dev/toolkits/creatomate) - Creatomate is an API for generating automated videos, images, GIFs, and reusable media templates. Use it to turn structured data into polished visual content at scale.
- [Cults](https://composio.dev/toolkits/cults) - Cults is a digital marketplace for 3D printing models, connecting designers and makers. It lets creators share, sell, and discover a huge variety of printable designs easily.
- [DeepImage](https://composio.dev/toolkits/deepimage) - DeepImage is an AI-powered image enhancer and upscaler. Get higher-quality images with just a few clicks.
- [Dreamstudio](https://composio.dev/toolkits/dreamstudio) - DreamStudio is Stability AI’s platform for generating and editing images with AI. It lets you easily turn ideas into stunning visuals, fast.
- [Dynamic Mockups](https://composio.dev/toolkits/dynamic_mockups) - Dynamic Mockups is an API platform for generating product mockups, rendering templates, and managing visual asset catalogs. Use it to automate high-quality product visuals, AI images, and motion assets at scale.
- [Dynapictures](https://composio.dev/toolkits/dynapictures) - Dynapictures is a cloud-based platform for generating personalized images at scale. Instantly create hundreds of custom visuals using your data sources, like Google Sheets.
- [Eraser MCP](https://composio.dev/toolkits/eraser_mcp) - Eraser MCP is a workspace for creating and managing technical diagrams and structured documents. It helps teams organize, version, and export diagrams with collaboration-focused tooling.
- [Excalidraw MCP](https://composio.dev/toolkits/excalidraw_mcp) - Excalidraw MCP is a no-auth MCP server for creating hand-drawn style diagrams in Excalidraw. Use it to generate visual sketches with viewport camera control and fullscreen editing.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Higgsfield MCP?

With a standalone Higgsfield MCP server, the agents and LLMs can only access a fixed set of Higgsfield tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Higgsfield and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with Hermes?

Yes, you can. Hermes fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Higgsfield tools.

### Can I manage the permissions and scopes for Higgsfield while using Tool Router?

Yes, absolutely. You can configure which Higgsfield scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Higgsfield data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)