# How to connect AllModels to Claude

```json
{
  "title": "How to connect AllModels to Claude",
  "toolkit": "AllModels",
  "toolkit_slug": "allmodels",
  "framework": "Claude Cowork",
  "framework_slug": "claude-cowork",
  "url": "https://composio.dev/toolkits/allmodels/framework/claude-cowork",
  "markdown_url": "https://composio.dev/toolkits/allmodels/framework/claude-cowork.md",
  "updated_at": "2026-11-17T05:32:21.668Z"
}
```

## 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 AllModels account to Claude via Composio Connect, enabling it to convert product announcements to natural speech, transcribe customer support call recordings, create a cloned voice for notifications, 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.
For exact tool slugs and parameter tables, see the [tool catalog in the Composio docs](https://docs.composio.dev/toolkits/allmodels).

## Also integrate AllModels with

- [ChatGPT](https://composio.dev/toolkits/allmodels/framework/chatgpt)
- [Hermes](https://composio.dev/toolkits/allmodels/framework/hermes-agent)
- [Atomic Agent](https://composio.dev/toolkits/allmodels/framework/atomic-agent)

## Connect AllModels to Claude Cowork

### Connecting AllModels 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 AllModels MCP server, and what's possible with it?

The AllModels MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your AllModels account. It provides structured and secure access to unified text-to-speech, speech-to-text, realtime voice, voice cloning, and account tools, so your agent can generate speech, transcribe audio, find models and voices, manage voice and realtime configurations, and review account activity on your behalf.
- Speech generation and transcription: Have your agent turn text into audio with OpenAI-compatible or ElevenLabs-compatible tools, or transcribe uploaded audio into text and timing data.
- Voice and model discovery: Let the agent search public voices, browse provider voices, and list available speech models with their supported capabilities and pricing.
- Voice cloning management: Direct your agent to create, inspect, list, download samples for, or delete organization-owned cloned voices.
- Realtime voice configuration: Instruct your agent to create, update, inspect, list, or delete realtime profiles and Speech Engines for conversational audio workflows.
- Account monitoring: Have your agent check API health, balance, usage, activity, transactions, and available credits, or create a top-up payment link when funds need to be added.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `ALLMODELS_ADD_SDK_VOICE` | Add SDK Voice | Clone one voice through the ElevenLabs voices.add compatibility endpoint. This mutation is the caller's attestation that the speaker consented and that the caller has rights to clone the uploaded recording. Creating the voice incurs a one-time provider cloning charge. |
| `ALLMODELS_CREATE_CUSTOM_VOICE` | Create Custom Voice | Clone a voice from an uploaded recording. This mutation attests that the speaker consented and that you have rights to use the sample. It may incur a one-time provider cloning fee; later speech generation is billed separately. The response can be pending: wait until both voice.status and providers[].status are active before generating speech. |
| `ALLMODELS_CREATE_REALTIME_CLIENT_SECRET` | Create Realtime Client Secret | Create a short-lived, single-use client secret and direct WebSocket URL from exactly one saved profile ID or complete inline profile. The returned secret and URL are ephemeral sensitive credentials and must not be logged or stored. |
| `ALLMODELS_CREATE_REALTIME_PROFILE` | Create Realtime Profile | Create a reusable Realtime speech pipeline or direct speech-to-speech profile with model routing, audio, conversation, client, lifecycle, limits, and tags. |
| `ALLMODELS_CREATE_SPEECH_ENGINE` | Create Speech Engine | Create a reusable Speech Engine that connects client audio to speech-to-text, an application WebSocket, and synthesized responses. |
| `ALLMODELS_CREATE_SPEECH_ENGINE_SIGNED_URL` | Create Speech Engine Signed URL | Create a short-lived, single-use WebSocket URL that lets one client connect to an existing Speech Engine without receiving the account API key. The returned URL contains an ephemeral credential and must be handled as a secret. |
| `ALLMODELS_CREATE_TOP_UP_LINK` | Create Top-Up Link | Create an expiring payment checkout link for adding a specified USD amount to the connected AllModels account. This initiates a financial top-up workflow by creating an external payment link, but does not itself charge a payment method or add funds; payment must be completed outside this action. |
| `ALLMODELS_DELETE_CUSTOM_VOICE` | Delete Custom Voice | Permanently delete an organization-owned cloned voice by voice_id. This destructive action cannot be undone, and deletion may take about a minute to finish. |
| `ALLMODELS_DELETE_REALTIME_PROFILE` | Delete Realtime Profile | Permanently delete a saved Realtime profile by profile_id. This destructive action cannot be undone. |
| `ALLMODELS_DELETE_SDK_VOICE` | Delete SDK Voice | Permanently delete an organization-owned cloned voice through the ElevenLabs voices.delete compatibility endpoint. This destructive action cannot be undone, and cached requests may keep using the voice for about one minute. |
| `ALLMODELS_DELETE_SPEECH_ENGINE` | Delete Speech Engine | Permanently delete a Speech Engine so it can no longer issue new signed conversation URLs. This destructive action cannot be undone. |
| `ALLMODELS_DOWNLOAD_CUSTOM_VOICE_SAMPLE` | Download Custom Voice Sample | Download the audio sample authorized by a short-lived custom-voice cloning token. |
| `ALLMODELS_GENERATE_OPENAI_SPEECH` | Generate OpenAI Speech | Generate speech through AllModels' OpenAI-compatible endpoint. Returns a downloadable audio file by default or the complete SSE event stream when stream_format is sse. This consumes the connected account's prepaid balance. |
| `ALLMODELS_GENERATE_SDK_SPEECH` | Generate SDK Speech | Generate a complete audio file through AllModels' ElevenLabs-compatible textToSpeech.convert endpoint. This consumes the connected account's prepaid balance. |
| `ALLMODELS_GET_ACCOUNT_BALANCE` | Get Account Balance | Return the connected account's paid and spendable credits, USD balance, availability state, and monthly-billing fields when present. |
| `ALLMODELS_GET_ACCOUNT_USAGE` | Get Account Usage | Return daily API-key usage and aggregate request, credit, and USD cost totals for a range of at most 90 days, optionally filtered by provider, model, or capability. Recent usage may take a short time to appear. |
| `ALLMODELS_GET_CUSTOM_VOICE` | Get Custom Voice | Return one organization-owned cloned voice, its readiness status, supported models, and provider status by voice_id. |
| `ALLMODELS_GET_OPENAI_CREDITS` | Get OpenAI Credits | Return available account funds in the OpenRouter-compatible credits envelope used by OpenAI-style clients. Use the account balance action for the detailed credit breakdown. |
| `ALLMODELS_GET_PROVIDER_SKILL` | Get Provider Skill | Return the provider-specific Markdown guide for steering TTS delivery through AllModels. |
| `ALLMODELS_GET_REALTIME_PROFILE` | Get Realtime Profile | Return one saved pipeline or speech-to-speech Realtime profile by its profile_id, including the complete nested configuration. |
| `ALLMODELS_GET_SDK_VOICE` | Get SDK Voice | Return one organization-owned cloned voice through the ElevenLabs voices.get compatibility endpoint. |
| `ALLMODELS_GET_SPEECH_ENGINE` | Get Speech Engine | Return one Speech Engine configuration by its speech_engine_id. |
| `ALLMODELS_HEALTH_CHECK` | Check API Health | Check whether the AllModels API and its LLM dependency are available, including nullable deployment commit identifiers. |
| `ALLMODELS_LIST_ACCOUNT_ACTIVITY` | List Account Activity | List individual API requests made with the connected API key, newest first, with time, provider, model, capability, and status filters plus an opaque continuation cursor. |
| `ALLMODELS_LIST_ACCOUNT_TRANSACTIONS` | List Account Transactions | List organization credit events such as top-ups, grants, refunds, adjustments, and expirations, returning one page and an opaque continuation cursor. |
| `ALLMODELS_LIST_CUSTOM_VOICES` | List Custom Voices | List the organization's cloned voices across projects, newest first by default, returning one cursor-controlled page. |
| `ALLMODELS_LIST_MODELS` | List Models | List available TTS, STT, and speech-to-speech models with aliases, provider capabilities, endpoints, instruction support, and pricing. |
| `ALLMODELS_LIST_PROVIDERS` | List Providers | List providers keyed by provider ID with their default models and voices, supported TTS/STT models, formats, capabilities, and pricing. |
| `ALLMODELS_LIST_REALTIME_PROFILES` | List Realtime Profiles | List saved Realtime profiles with name search, sort direction, and one cursor-controlled page. |
| `ALLMODELS_LIST_SDK_VOICES` | List SDK Voices | List voices from one TTS provider in the ElevenLabs voices.get_all compatibility envelope. |
| `ALLMODELS_LIST_SPEECH_ENGINES` | List Speech Engines | List permanent Speech Engines with name search, sort controls, and one cursor-controlled page. |
| `ALLMODELS_SEARCH_SDK_VOICES` | Search SDK Voices | List voices for one text-to-speech provider in the ElevenLabs SDK search compatibility envelope, optionally limiting the single returned page. |
| `ALLMODELS_SEARCH_VOICES` | Search Voices | Search the public voice catalogue by text, model, provider, language, category, labels, and sort order, returning one cursor-controlled page. |
| `ALLMODELS_START_AGENT_SIGNUP` | Start Agent Signup | Send a six-digit AllModels access code to an account owner's email address. This action requires a connected AllModels API key and has an external email side effect. After receiving the code, verify it with the same email address. The verification action returns a new or replacement key that must be used to create a new connection; it does not update the current connection. AllModels publishes no numeric request quota, but may return 429; wait for the Retry-After interval before requesting another code. |
| `ALLMODELS_STREAM_SDK_SPEECH` | Stream SDK Speech | Generate speech through the ElevenLabs-compatible streaming HTTP endpoint and return the produced audio as a downloadable file. This consumes the connected account's prepaid balance. |
| `ALLMODELS_TRANSCRIBE_OPENAI_AUDIO` | Transcribe OpenAI Audio | Transcribe an uploaded audio file through AllModels' OpenAI-compatible endpoint and preserve JSON, text, subtitle, or SSE output. This consumes the connected account's prepaid balance. |
| `ALLMODELS_TRANSCRIBE_SDK_AUDIO` | Transcribe SDK Audio | Transcribe an uploaded audio file through AllModels' ElevenLabs-compatible endpoint and return text, language, and available word or character timing. This consumes the connected account's prepaid balance. |
| `ALLMODELS_UPDATE_REALTIME_PROFILE` | Update Realtime Profile | Patch selected fields of a saved pipeline or speech-to-speech Realtime profile. Omitted fields remain unchanged, explicit null values are retained, and a missing profile is not created. |
| `ALLMODELS_UPDATE_SPEECH_ENGINE` | Update Speech Engine | Partially update an existing AllModels Speech Engine. Only explicitly supplied configuration fields are changed; use the STT and TTS extensions for non-ElevenLabs model routing or settings without a standard Speech Engine field. |
| `ALLMODELS_VERIFY_AGENT_SIGNUP` | Verify Agent Signup | Verify an emailed six-digit AllModels signup code using the same email address that requested it. This action requires a connected AllModels API key. Success creates and returns a sensitive new or replacement API key in full only once; store it securely and use it to create a new connection because this action cannot update the current connection. Never log, cache, place the key in fixtures, or share it. If claimUrl is returned, give it only to the account owner so they can claim free credit in a browser; it does not sign them in. If the code expired or was already used, start the signup flow again. |

## Supported Triggers

None listed.

## Troubleshooting

### 1. Why does Claude not use the Composio connector for AllModels?

The connector can show as connected, but Claude must use it in each AllModels conversation.
- Click + at the lower left of the chat, or type /.
- Hover Connectors.
- Turn on Composio.
- Ask Claude to connect to AllModels again.

### 2. Why does Claude show an MCP server error before AllModels connects?

Claude can show Couldn't reach the MCP server or Authorization with the MCP server failed when you add the connector for AllModels.
- 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 AllModels.
- If it fails again, send the error and the ofid_ reference id to support@composio.dev.

### 3. Why does the AllModels authorization link not work?

The Composio connector is one server. Your AllModels account connects separately when Claude asks for it.
- If the browser does not open, or the link expires, ask Claude to retry the AllModels connection.
- Composio creates a fresh AllModels authorization link.
- Open that link in your browser and finish the AllModels sign-in.

### 4. Why do AllModels actions fail after they worked before?

The AllModels connection can expire or lose permission.
- Ask Claude to inspect the AllModels connection.
- If the connection is unhealthy, disconnect it when Claude prompts you.
- Reconnect the AllModels account and retry the action.
- If Claude shows a permission prompt, approve it before Claude changes data in AllModels.
- If the action still fails with a permission error, check that the connected account has that permission in AllModels itself.

### 5. How do I switch to a different AllModels account?

Claude can manage the AllModels connection for you.
- Ask Claude to disconnect or delete the current AllModels account.
- Ask Claude to connect AllModels again.
- Open the new Composio authorization link for AllModels.
- Sign in with the other AllModels account in the browser.
- After the account connects, ask Claude to retry the AllModels task.

### 6. Why is my AllModels connection missing in Claude Desktop or on a Team plan?

The connector belongs to your Claude account, so your AllModels connection works in Claude Web, Desktop, and Cowork.
- In Claude Desktop, open Customize > Connectors.
- Next to Composio, click ⋮ and click Clear cache.
- If AllModels 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 AllModels.

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

The AllModels MCP server connects Claude Web, Desktop, and Cowork to your AllModels account through Composio. Once connected, Claude can use the available AllModels tools and triggers to complete tasks on your behalf.

## Complete Code

None listed.

## How to build AllModels MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/allmodels/framework/chatgpt)
- [Hermes](https://composio.dev/toolkits/allmodels/framework/hermes-agent)
- [Atomic Agent](https://composio.dev/toolkits/allmodels/framework/atomic-agent)

## Related Toolkits

- [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed.
- [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service.
- [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows.
- [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow.
- [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows.
- [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application.
- [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities.
- [AltTextLab](https://composio.dev/toolkits/alt_text_lab) - AltTextLab is an AI service that generates accessible, SEO-aware alt text for images. It helps teams make image content easier to understand, index, and publish.
- [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization.
- [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications.
- [Apiframe](https://composio.dev/toolkits/apiframe) - Apiframe is an API platform for generating and managing AI images, videos, music, uploads, assets, jobs, and custom LoRAs. It gives developers one clean API for creative AI workflows without juggling multiple model providers.
- [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations.
- [Arize AX](https://composio.dev/toolkits/arize_ax) - Arize AX is an AI engineering platform for tracing, evaluating, and improving AI applications. Use it to debug LLM behavior, compare experiments, and improve production AI quality.
- [Artificial Analysis](https://composio.dev/toolkits/artificial_analysis) - Artificial Analysis is an independent benchmarking platform for AI models and API providers. Use it to compare model intelligence, coding, math, pricing, latency, throughput, and arena rankings.
- [AssemblyAI](https://composio.dev/toolkits/assemblyai) - AssemblyAI is a speech-to-text and audio intelligence API for uploaded or hosted media. Use it to turn audio and video into accurate transcripts, summaries, and insights.
- [Astica ai](https://composio.dev/toolkits/astica_ai) - Astica ai provides APIs for computer vision, NLP, and voice synthesis. Integrate advanced AI features into your app with a single API key.
- [Avoma](https://composio.dev/toolkits/avoma) - Avoma is an AI meeting assistant for recording, transcribing, analyzing, and managing meetings, calls, notes, scorecards, and conversation intelligence. It helps teams turn conversations into searchable notes, follow-ups, coaching insights, and revenue intelligence.
- [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient.
- [Black Forest Labs](https://composio.dev/toolkits/bfl) - Black Forest Labs provides hosted FLUX models for generating and editing images and videos. It offers fast, flexible media creation with asynchronous processing and fine-tuning support.
- [Bland AI](https://composio.dev/toolkits/bland_ai) - Bland AI is a conversational AI platform for building voice agents, phone calls, messaging, and communication workflows. Use it to automate calling, evaluate conversations, and run voice operations at scale.

## Frequently Asked Questions

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

With a standalone AllModels MCP server, the agents and LLMs can only access a fixed set of AllModels tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from AllModels 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 AllModels tools.

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

Yes, absolutely. You can configure which AllModels 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 AllModels data and credentials are handled as safely as possible.

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