SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to connect LLM API to Claude

Connect Claude Web, Desktop and Cowork to LLM API MCP. Generate embeddings for product descriptions, create an image from a product brief, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
LLM API logoLLM API
Api Key

LLM API is a unified inference service for text, embeddings, images, audio, video, files, and batch workloads across AI providers. It gives teams one consistent API for accessing multiple models and media capabilities.

12 Tools

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

ChatGPTHermesAtomic Agent

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

Add manually

In Claude Desktop, click Customize in the left sidebar, then select Connectors and click the + icon at the top.

Claude Desktop connectors screen with Add custom connector selected

Click Add custom connector and paste in the Composio MCP server URL:

bash
https://connect.composio.dev/mcp
Add custom connector dialog with Composio MCP server URL

2. Authorize in your browser

Click Connect. You'll be redirected to a browser window where you can authorize Composio to continue.

Composio authorization screen for Claude Web, Desktop, and Cowork

3. Connect your LLM API account

Back in Claude, ask it to connect to LLM API or give it any LLM API-related task.

For example, ask Claude to:

  • "Generate embeddings for product descriptions"
  • "Create an image from a product brief"
  • "Transcribe an uploaded customer call"

It will prompt you to authenticate and authorize access.

That's it. Composio's tools are now available in Claude, and your LLM API account is ready to use.

What is the LLM API Claude Connector, 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.

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.
TOOLS

Supported Tools

Every LLM API action and event your agent gets out of the box.

Cancel Batch

Request best-effort cancellation of an in-progress batch.

Count Anthropic Message Tokens

Count input tokens for an Anthropic-compatible message request without generating a model response.

Create Anthropic Message

Generate one complete, non-streaming Anthropic-compatible message with flexible content blocks, system prompts, and tool use with your own connection.

Create Chat Completion

Generate a complete, non-streaming OpenAI-compatible chat response.

Create Embeddings

Create vector embeddings for one text or a batch of texts with a selected embedding model.

Create Response

Generate one complete, non-streaming OpenAI Responses-compatible result from text or structured input, preserving reasoning and tool items.

Delete File

Permanently delete a caller-owned or explicitly authorized project file.

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.

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.

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 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.

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.

FRAMEWORKS

How to build LLM API MCP Agent with another framework

ChatGPT logo

ChatGPT

Use LLM API MCP with ChatGPT

Hermes logo

Hermes

Use LLM API MCP with Hermes

Atomic Agent logo

Atomic Agent

Use LLM API MCP with Atomic Agent

FAQ

Frequently asked questions

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.

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.

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.

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.

Start with LLM API.It takes 30 seconds.

Managed auth, hosted MCP servers, and every LLM API tool your agent needs.Free to start.

Start building