# How to connect Recraft MCP to Claude ```json { "title": "How to connect Recraft MCP to Claude", "toolkit": "Recraft MCP", "toolkit_slug": "recraft_mcp", "framework": "Claude Cowork", "framework_slug": "claude-cowork", "url": "https://composio.dev/toolkits/recraft_mcp/framework/claude-cowork", "markdown_url": "https://composio.dev/toolkits/recraft_mcp/framework/claude-cowork.md", "updated_at": "2026-10-22T05:32:12.794Z" } ``` ## Introduction Claude is Anthropic's AI assistant, available on the web, in the desktop app, and on mobile. Cowork is its agent for knowledge work, and it runs on all of those surfaces too. Connected to your apps, Claude can work with your files and services to accomplish complex tasks on your behalf. This guide walks you through the easiest and most secure way to connect your Recraft account to Claude via Composio Connect, enabling it to generate a product illustration in your custom style, edit this image into a poster design, inspect your Recraft account usage details, and more such actions on your behalf without compromising your account security. Setup is the same on Claude Web, Desktop, and Cowork, and you only need to do it once. The connector is tied to your account, so it's available in all three. ## Also integrate Recraft MCP with - [ChatGPT](https://composio.dev/toolkits/recraft_mcp/framework/chatgpt) - [Hermes](https://composio.dev/toolkits/recraft_mcp/framework/hermes-agent) - [Atomic Agent](https://composio.dev/toolkits/recraft_mcp/framework/atomic-agent) ## Connect Recraft MCP to Claude Cowork ### Connecting Recraft to Claude Web, Desktop, and Cowork Two ways to add the Composio connector. Pick whichever you prefer. ### 1. Add with one click Click the button. Claude opens with the Composio connector filled in. Click Add, then go to step 2. [Add to Claude](https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Composio&connectorUrl=https%3A%2F%2Fconnect.composio.dev%2Fmcp) ### Add manually In Claude Desktop, click Customize in the left sidebar, then select Connectors and click the + icon at the top. Click Add custom connector and paste in the Composio MCP server URL: ```bash https://connect.composio.dev/mcp ``` ## What is the Recraft MCP server, and what's possible with it? The Recraft MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Recraft account. It provides structured and secure access to Recraft's image generation, editing, upscaling, vectorization, style management, and account tools, so your agent can create visual assets, modify images, apply custom styles, and check your Recraft usage on your behalf. - Image generation and variations: Have your agent generate images from text prompts, create variations of existing images, transform images with image-to-image instructions, and choose a suitable model for a request. - Image editing and background work: Let the agent edit images from prompts, inpaint or erase selected regions, remove or replace backgrounds, and generate new backgrounds for masked areas. - Image enhancement and vectorization: Direct your agent to use creative or crisp upscaling for supported images, or convert raster artwork into a vector format. - Custom visual styles: Instruct your agent to create styles from reference images, list available custom or built-in styles, inspect a style's details, or delete a custom style. - Account and plan information: Have your agent check your Recraft profile and remaining credits, or review available subscription plans and their credit allowances. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `RECRAFT_MCP_CALL_AGENT` | Call agent | Talk to Recraft's Design Agent in a chat. This is not just any agent — it is The Design Agent, and its superpower is turning a brief — a plain description of a digital product — into a strong, consistent and genuinely amazing set of design assets. Building a coherent look normally means juggling separate tools — one for the logo, another for icons, another for social assets — and without a designer to hold it together the result feels like five apps that have never met. The Design Agent does it all at once: describe the product and it produces a full, consistent set of design assets — a logo, a colour palette, typography, an app icon and social assets among them — and can save them as a reusable Design Kit so every asset pulled from it later stays consistent. It is built for digital products: apps, websites and similar projects. Reach for it whenever the user needs a whole coherent look rather than a single one-off image. This is a two-way, turn-based conversation, not a one-shot request: you send a text message (optionally with input images) and receive the agent's combined reply, which may include images the agent generates. The agent often drives the exchange itself — instead of a final result it may reply with a clarifying question or a set of choices (for example confirming it should proceed, asking for visual references or a preferred direction, or asking which option to develop). When it does, relay that reply to the end user verbatim, collect their answer, and send it back in a follow-up call — do not answer on the user's behalf or skip ahead. A single task can take several turns before the agent produces its final design assets. Omit chat_id to start a new conversation; the response contains the chat_id — pass it in every subsequent call to continue the same conversation with full context. Images flow both ways. To send images to the agent, provide input_image_urls, a list of publicly accessible HTTP or HTTPS URLs (PNG, JPEG, WEBP or SVG); if you only have local image files, call request_upload_url first, PUT the image bytes to the returned upload URL, and pass the resulting image_url values here. Any images the agent generates come back in the response. The response contains the agent's text answer, the chat_id, URLs of any generated images with WEBP previews as base64 encoded bytes, and the credits this call used. | | `RECRAFT_MCP_CREATE_STYLE` | Create style | Create a custom style from one or more reference images. Provide images via URLs or base64-encoded data. The `input_style` parameter defines the base style type. The style is saved to the user's Recraft account, so it is also available in the Recraft app. Returns the new style ID, which you can pass as `input_style_id` to the generation tools. Creating a style is free. | | `RECRAFT_MCP_CREATIVE_UPSCALE` | Creative upscale | Input must have at most 4194304 pixels (4 MP), sides from 256 to 4096 pixels, and at most 48 MiB of raster data. Larger inputs are rejected before generation or billing. Upscale an image using creative AI enhancement. Provide a publicly accessible HTTP or HTTPS URL as `input_image_url`. If you only have a local image file with no public URL, call `request_upload_url` first, PUT the image bytes to the returned upload URL, and pass the resulting `image_url` here. Returns the processed image as a URL and a preview in WEBP format as a base64 encoded bytes. | | `RECRAFT_MCP_CRISP_UPSCALE` | Crisp upscale | Input must have at most 4194304 pixels (4 MP), sides from 32 to 4096 pixels, and at most 48 MiB of raster data. Upscale an image with sharp, crisp quality enhancement. Provide a publicly accessible HTTP or HTTPS URL as `input_image_url`. If you only have a local image file with no public URL, call `request_upload_url` first, PUT the image bytes to the returned upload URL, and pass the resulting `image_url` here. Returns the processed image as a URL and a preview in WEBP format as a base64 encoded bytes. | | `RECRAFT_MCP_DELETE_STYLE` | Delete style | Delete a custom style by its `style_id`. This cannot be undone. | | `RECRAFT_MCP_ERASE_REGION` | Erase region | Erase a masked region from an image, filling it with content-aware background. Provide the source image as `input_image_url` and a mask image as `mask_image_url`, both publicly accessible HTTP or HTTPS URLs. If you only have local image files with no public URLs, call `request_upload_url` for each, PUT the image bytes to each returned upload URL, and pass the resulting `image_url` values here. Returns the processed image as a URL and a preview in WEBP format as a base64 encoded bytes. | | `RECRAFT_MCP_GENERATE_BACKGROUND` | Generate background | Generate a background for a masked region of an image based on a text prompt. Provide the source image as `input_image_url` and a mask image as `mask_image_url`, both publicly accessible HTTP or HTTPS URLs. If you only have local image files with no public URLs, call `request_upload_url` for each, PUT the image bytes to each returned upload URL, and pass the resulting `image_url` values here. Returns an image_urls array and previews in WEBP format as a base64 encoded bytes. | | `RECRAFT_MCP_GENERATE_IMAGE` | Generate image | Generate an image from a text prompt. You can specify the image size, style, model, and number of images to generate. You don't need to change default parameters if you don't have any specific requirements. Recraft has both raster and vector models. Recraft models come in a `_raster` and a `_vector` variant: a raster model (e.g. recraftv4_1_raster) produces a raster image (PNG/WEBP), while a vector model (e.g. recraftv4_1_vector) produces a true SVG vector file. Whenever the user asks for a vector, an SVG, a scalable logo, or an icon, pass the `_vector` variant of the model — that is the reliable way to get an SVG. Use the `_raster` variant for photos and raster artwork. recraftv4_1_flash_raster has no vector variant. See the `model` parameter for the full list of variants. Besides Recraft models, this tool supports external models such as nano_banana_2, nano_banana_pro, gpt_image_2_medium or bytedance_seedreamv5_pro (see the `model` parameter for the full list); availability depends on your subscription and is validated server-side. External models produce raster images only: they have no `_vector` variants, cannot generate SVG, and do not support custom styles. Recraft also has a large library of built-in "basic styles" beyond the default models. Call the `list_basic_styles` tool to explore the full variety of available styles, then apply a chosen one via its `input_style_id`. To apply a basic or custom style, pass its `input_style_id` (see list_basic_styles, list_styles and create_style) and omit `input_style`: the image type is taken from the style. URLs to generated images, their previews in WEBP format as base64 encoded bytes and the credits the call used will be returned in the response. | | `RECRAFT_MCP_GET_STYLE` | Get style | Get details of a specific style by its `style_id`: its name, type, model and privacy. | | `RECRAFT_MCP_GET_USER` | Get user | Get information about the current user (ID, email, name, and the remaining credits balance on the account). | | `RECRAFT_MCP_IMAGE_EDIT` | Image edit | Edit one or more input images according to a text prompt, producing new image(s). Use this tool for instruction-driven editing: describe the change you want (for example "add a hat", "make it winter", "replace the text with SALE", or "combine these images") and the model rewrites the image to follow the prompt. It can take several input images at once and can use external models. Choose image_edit when you want the model to follow explicit editing instructions or to use an external model; choose image_to_image instead when you want a strength-controlled stylistic transformation of a single image rather than a specific edit. Provide the source images as `input_image_urls` — a list of publicly accessible HTTP or HTTPS URLs (PNG, JPEG, WEBP or SVG). If you only have local image files with no public URL, call `request_upload_url` for each, PUT the image bytes to the returned upload URL, and pass the resulting `image_url` values here. You can specify the image size, model, and number of images to generate. You don't need to change default parameters if you don't have any specific requirements. This tool works only with external models; Recraft models are not supported for instruction-driven editing. External models produce raster images only: they cannot generate SVG and do not support custom styles. The default model is nano_banana_2; others include nano_banana_pro, nano_banana_2p1, gpt_image_2_medium, gpt_image_2p5_flare and bytedance_seedreamv5_pro (see the `model` parameter for the full list). Availability depends on your subscription and is validated server-side. If the image size is not specified, the output size follows the first input image. URLs to the edited images, their previews in WEBP format as base64 encoded bytes and the credits the call used will be returned in the response. | | `RECRAFT_MCP_IMAGE_TO_IMAGE` | Image to image | Transform an existing image based on a text prompt. The strength parameter controls how much the image is transformed (0.0 to 1.0). Provide a publicly accessible HTTP or HTTPS URL as `input_image_url`. Use this tool for a strength-controlled stylistic transformation of a single image, where the prompt and style reshape the whole image and `strength` sets how far the result moves from the original. For instruction-driven edits (changing or adding specific elements, editing several images together, or using an external model such as nano_banana_pro or flux1_kontext_pro), use the image_edit tool instead. If you only have a local image file with no public URL, call `request_upload_url` first, PUT the image bytes to the returned upload URL, and pass the resulting `image_url` here. Returns an image_urls array and previews in WEBP format as a base64 encoded bytes. | | `RECRAFT_MCP_INPAINT_IMAGE` | Inpaint image | Fill in a masked region of an image based on a text prompt. Provide the source image as `input_image_url` and a mask image as `mask_image_url`, both publicly accessible HTTP or HTTPS URLs. If you only have local image files with no public URLs, call `request_upload_url` for each, PUT the image bytes to each returned upload URL, and pass the resulting `image_url` values here. Returns an image_urls array and previews in WEBP format as a base64 encoded bytes. | | `RECRAFT_MCP_LIST_BASIC_STYLES` | List basic styles | Lists the built-in styles configured in this environment; coverage differs by model. The returned model is a compatible generation identifier. Passing input_style_id can select an older model instead of the default v4.1. List Recraft's library of built-in "basic styles" — a large, curated collection of visual styles for image generation that goes well beyond the default models. Call this to explore the full variety of available styles and pick the one that best matches the user's request. Returns a list of styles, each with a `style_name`, its `input_style_id`, its type and the model it belongs to. Apply a chosen style by passing its `input_style_id` to the generation tools (generate_image, image_to_image, etc.); omit `model` to use the style's own model. | | `RECRAFT_MCP_LIST_STYLES` | List styles | List all custom styles created by the current user. Returns a list of style IDs with their names, types (the image type generations with the style produce), models and privacy. Pass a style ID as `input_style_id` to the generation tools. | | `RECRAFT_MCP_REMOVE_BACKGROUND` | Remove background | Remove the background from an image. Provide a publicly accessible HTTP or HTTPS URL as `input_image_url`. If you only have a local image file with no public URL, call `request_upload_url` first, PUT the image bytes to the returned upload URL, and pass the resulting `image_url` here. Returns the processed image with background removed as a URL and a preview in WEBP format as a base64 encoded bytes. | | `RECRAFT_MCP_REPLACE_BACKGROUND` | Replace background | Replace the background of an image based on a text prompt. Provide a publicly accessible HTTP or HTTPS URL as `input_image_url`. If you only have a local image file with no public URL, call `request_upload_url` first, PUT the image bytes to the returned upload URL, and pass the resulting `image_url` here. Returns an image_urls array and previews in WEBP format as a base64 encoded bytes. | | `RECRAFT_MCP_REQUEST_UPLOAD_URL` | Request upload url | Issue an upload URL for a direct image upload. Use this when the user provides a local image file (or raw image data) that has no public URL of its own. If the user already provided a public HTTPS image URL, pass that URL directly to the image tools instead — do NOT route it through this step. This tool takes no parameters and returns an `upload_url` plus a ready-to-run `curl` command. PUT the raw image bytes directly to `upload_url` (no base64, no encoding) with a `Content-Type` header matching the image MIME type (image/png, image/jpeg or image/webp), e.g.: curl -X PUT -H 'Content-Type: image/png' --data-binary @image.png '' The PUT response is JSON containing `image_url`. Use that `image_url` as `input_image_url` (or `mask_image_url`) when calling any image tool such as image_to_image, remove_background, inpaint_image, etc. The link is reusable for up to 15 minutes while session authorization remains valid; request a new link after a 401 response. | | `RECRAFT_MCP_SUBSCRIPTION_PLANS` | Subscription plans | List available Recraft subscription plans with their plan IDs, credits granted per refill period, and prices. | | `RECRAFT_MCP_SUGGEST_MODEL` | Suggest model | Suggest a supported image generation or instruction-editing model for a given user request. Returns JSON with model_suggestion (an exact supported model identifier) and reason. Covers Recraft generation and external instruction-editing models. Chooses a Recraft `_vector` model for SVG output and an image_edit model for instruction editing; honors an explicitly requested supported model. | | `RECRAFT_MCP_VARIATE_IMAGE` | Variate image | Generate variations of an existing image. Set the required image_size parameter to an output aspect ratio. Provide a publicly accessible HTTP or HTTPS URL as `input_image_url`. If you only have a local image file with no public URL, call `request_upload_url` first, PUT the image bytes to the returned upload URL, and pass the resulting `image_url` here. Returns an image_urls array and previews in WEBP format as a base64 encoded bytes. | | `RECRAFT_MCP_VECTORIZE_IMAGE` | Vectorize image | Convert a raster image to a vector format. Provide a publicly accessible HTTP or HTTPS URL as `input_image_url`. If you only have a local image file with no public URL, call `request_upload_url` first, PUT the image bytes to the returned upload URL, and pass the resulting `image_url` here. Returns the processed image as a URL and a preview in WEBP format as a base64 encoded bytes. | ## Supported Triggers None listed. ## Troubleshooting ### 1. Why does Claude not use the Composio connector for Recraft? The connector can show as connected, but Claude must use it in each Recraft conversation. - Click + at the lower left of the chat, or type /. - Hover Connectors. - Turn on Composio. - Ask Claude to connect to Recraft again. ### 2. Why does Claude show an MCP server error before Recraft connects? Claude can show Couldn't reach the MCP server or Authorization with the MCP server failed when you add the connector for Recraft. - Check that the connector URL is https://connect.composio.dev/mcp. - Connectors run from Anthropic's cloud, so your device network is usually not the problem. - Add the connector again from Customize > Connectors, then ask Claude to connect Recraft. - If it fails again, send the error and the ofid_ reference id to support@composio.dev. ### 3. Why does the Recraft authorization link not work? The Composio connector is one server. Your Recraft account connects separately when Claude asks for it. - If the browser does not open, or the link expires, ask Claude to retry the Recraft connection. - Composio creates a fresh Recraft authorization link. - Open that link in your browser and finish the Recraft sign-in. ### 4. Why do Recraft actions fail after they worked before? The Recraft connection can expire or lose permission. - Ask Claude to inspect the Recraft connection. - If the connection is unhealthy, disconnect it when Claude prompts you. - Reconnect the Recraft account and retry the action. - If Claude shows a permission prompt, approve it before Claude changes data in Recraft. - If the action still fails with a permission error, check that the connected account has that permission in Recraft itself. ### 5. How do I switch to a different Recraft account? Claude can manage the Recraft connection for you. - Ask Claude to disconnect or delete the current Recraft account. - Ask Claude to connect Recraft again. - Open the new Composio authorization link for Recraft. - Sign in with the other Recraft account in the browser. - After the account connects, ask Claude to retry the Recraft task. ### 6. Why is my Recraft connection missing in Claude Desktop or on a Team plan? The connector belongs to your Claude account, so your Recraft connection works in Claude Web, Desktop, and Cowork. - In Claude Desktop, open Customize > Connectors. - Next to Composio, click ⋮ and click Clear cache. - If Recraft tools still do not appear, click ⋮, disconnect, remove the connector, and add it again. - On Team or Enterprise, an Owner or Primary Owner must enable the connector before you can connect Recraft. ## Creating MCP Server - Stand-alone vs Composio SDK The Recraft MCP server connects Claude Web, Desktop, and Cowork to your Recraft account through Composio. Once connected, Claude can use the available Recraft tools and triggers to complete tasks on your behalf. ## Complete Code None listed. ## How to build Recraft MCP Agent with another framework - [ChatGPT](https://composio.dev/toolkits/recraft_mcp/framework/chatgpt) - [Hermes](https://composio.dev/toolkits/recraft_mcp/framework/hermes-agent) - [Atomic Agent](https://composio.dev/toolkits/recraft_mcp/framework/atomic-agent) ## 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. - [BeatAPI](https://composio.dev/toolkits/beatapi) - BeatAPI is an asynchronous API platform for AI image, video, and music workflows. It enables scalable generation, video analysis, uploads, and ecommerce video pipelines. - [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. - [Dribbble](https://composio.dev/toolkits/dribbble) - Dribbble is a design community and publishing platform for managing shots, projects, and attachments. Use it to showcase work, collect feedback, and organize creative designs. - [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. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Recraft MCP? With a standalone Recraft MCP server, the agents and LLMs can only access a fixed set of Recraft tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Recraft and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with Claude Cowork? Yes, you can. Claude Cowork 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 Recraft tools. ### Can I manage the permissions and scopes for Recraft while using Tool Router? Yes, absolutely. You can configure which Recraft 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 Recraft data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)