# How to connect LLM API to Claude

```json
{
  "title": "How to connect LLM API to Claude",
  "toolkit": "LLM API",
  "toolkit_slug": "llm_api",
  "framework": "Claude Cowork",
  "framework_slug": "claude-cowork",
  "url": "https://composio.dev/toolkits/llm_api/framework/claude-cowork",
  "markdown_url": "https://composio.dev/toolkits/llm_api/framework/claude-cowork.md",
  "updated_at": "2026-11-01T07:20:22.117Z"
}
```

## 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 LLM API account to Claude via Composio Connect, enabling it to generate embeddings for product descriptions, create an image from a product brief, transcribe an uploaded customer call, 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 LLM API with

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

## Connect LLM API to Claude Cowork

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

The LLM API MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your LLM API account. It provides structured and secure access to text generation, embeddings, model capabilities, files, batch workloads, and account credits, so your agent can generate responses, create embeddings, discover suitable models, manage files and batch jobs, and check available credits on your behalf.
- Multi-provider text generation: Have your agent create chat completions, responses, or Anthropic-compatible messages with text, structured inputs, tool use, and supported multimodal content.
- Embedding creation: Let the agent turn one text or a group of texts into vector embeddings for search, matching, and other AI workflows.
- Model discovery: Direct your agent to browse available models or inspect a model’s live capabilities before choosing one for a task.
- File and batch workload management: Instruct your agent to list or retrieve project files, remove files, submit asynchronous batch workloads, and check or cancel batches.
- Credit and account status: Have your agent review connected user details, project information, credit balances, funding mode, and balance limits.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `LLM_API_CANCEL_BATCH` | Cancel Batch | Request best-effort cancellation of an in-progress batch. Return the provider's actual batch state without implying cancellation took effect; work may still finish and incur charges before the request is applied. |
| `LLM_API_COUNT_ANTHROPIC_MESSAGE_TOKENS` | Count Anthropic Message Tokens | Count input tokens for an Anthropic-compatible message request without generating a model response. |
| `LLM_API_CREATE_ANTHROPIC_MESSAGE` | Create Anthropic Message | Generate one complete, non-streaming Anthropic-compatible message with flexible content blocks, system prompts, and tool use with your own connection. Instant supports the Claude models listed in its pricing, with plain-text messages and a plain-text system prompt; tools, content blocks and other models are rejected before provider execution. |
| `LLM_API_CREATE_CHAT_COMPLETION` | Create Chat Completion | Generate a complete, non-streaming OpenAI-compatible chat response. Instant supports only the models listed in its pricing, with plain-text messages: no tools, multimodal content, web search, or reasoning-effort overrides. Unsupported Instant requests are rejected before provider execution. With your own connection, use models and capabilities supported by your provider project. |
| `LLM_API_CREATE_EMBEDDINGS` | Create Embeddings | Create vector embeddings for one text or a batch of texts with a selected embedding model. Requires your own connection; this action is unavailable through Instant. |
| `LLM_API_CREATE_RESPONSE` | Create Response | Generate one complete, non-streaming OpenAI Responses-compatible result from text or structured input, preserving reasoning and tool items. Requires your own connection; this action is unavailable through Instant. |
| `LLM_API_DELETE_FILE` | Delete File | Permanently delete a caller-owned or explicitly authorized project file. This destructive operation cannot be undone; a missing file fails with not found rather than reporting a successful deletion. |
| `LLM_API_DISCOVER_MODELS` | Discover Models | Return one model's full live capabilities by ID, or browse a compact, bounded view of the live model catalog using local capability filters. |
| `LLM_API_GET_ACCOUNT_AND_CREDITS` | Get Account and Credits | Return the connected user, project, organization, purchased and bonus credit balances, funding mode, and balance gating in one account-status read. |
| `LLM_API_LIST_OR_GET_BATCHES` | List or Get Batches | Return one asynchronous batch and its latest lifecycle, token, and cost status by ID, or one provider-default page of project batches when no batch ID is supplied. List mode supports provider cursor pagination. |
| `LLM_API_LIST_OR_GET_FILES` | List or Get Files | Return metadata for one project file by ID, or one provider-default page of project file metadata when no file ID is supplied. List mode supports purpose filtering and provider cursor pagination. |
| `LLM_API_SUBMIT_BATCH` | Submit Batch | Create an asynchronous batch from an existing purpose=batch file ID, or upload a JSONL input file with purpose=batch and create the batch in one call. |

## Supported Triggers

None listed.

## Troubleshooting

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

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

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

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

### 3. Why does the LLM API authorization link not work?

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

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

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

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

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

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

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

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

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

## Complete Code

None listed.

## How to build LLM API MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/llm_api/framework/chatgpt)
- [Hermes](https://composio.dev/toolkits/llm_api/framework/hermes-agent)
- [Atomic Agent](https://composio.dev/toolkits/llm_api/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.
- [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.
- [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.
- [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.
- [Botbaba](https://composio.dev/toolkits/botbaba) - Botbaba is a platform for building, managing, and deploying conversational AI chatbots across messaging channels. It streamlines chatbot automation, making it easier to integrate AI into customer interactions.
- [BotMape](https://composio.dev/toolkits/botmape) - BotMape is an API platform for building AI agents, knowledge bases, conversations, and messages. Use it to manage agent workflows and track usage analytics from one place.
- [Botpress](https://composio.dev/toolkits/botpress) - Botpress is an open-source platform for building, deploying, and managing chatbots. It helps teams automate conversations and deliver rich, interactive messaging experiences.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and LLM API MCP?

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

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

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

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