How to Use the LibreChat MCP in Claude

Q: How do I configure LibreChat inside the Claude Desktop app?

Open your claudedesktopconfig.json file and add the MCP Server configuration under the mcpServers block with your server URL. Restart Claude Desktop completely, and you will see the tools available via the hammer icon in your chat window.

Q: Why does my LibreChat session expire in Claude Desktop?

If your session expires, you need to run the login tool again to generate fresh access and refresh tokens. Claude Desktop stores these tokens locally to keep your connection to the LibreChat API active.

Q: How does the openresponses tool differ from chatcompletions?

The openresponses tool accesses the raw Open Responses API for direct text generation. In contrast, chatcompletions routes your prompts through specific LibreChat Agent IDs, applying their pre-configured system prompts and tools.

Run your LibreChat agents and model completions directly inside Claude Desktop.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LibreChat MCP to Claude Desktop

Create your Vinkius account to connect LibreChat to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup LibreChat with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run LibreChat agent completions directly in Claude Desktop

The `chat_completions` tool lets you trigger specific LibreChat Agent IDs right from your desktop chat interface. You don't need to jump between browser tabs to access your custom-configured agents anymore. Claude Desktop uses local stdio transport to execute this MCP server tool as a subprocess, feeding your prompt straight to your self-hosted LibreChat setup. When you ask Claude Desktop to run a task, it checks your active session and routes the payload to the designated Agent ID. This keeps your custom system prompts and agent configurations intact while you work inside your local desktop environment.

Authenticate and fetch available models on the fly

The `login` tool handles your session state, generating the access and refresh tokens needed to talk to your LibreChat backend securely. This authentication flow runs directly within the Claude Desktop config setup, keeping your credentials isolated on your local machine. Once logged in, your agent can call `list_models` to pull the exact list of active LLMs and customized agents configured on your instance. This ensures you only send prompts to models that are currently online and configured on your server.

Generate fast text outputs with Open Responses

The `open_responses` tool executes raw text generation tasks through the LibreChat Open Responses API. If you use Claude Web with custom connectors, this remote MCP Server connection lets you bypass heavier agent pipelines for fast, direct text generation. It works by sending your raw prompt straight to the backend without the overhead of agent state management. This is perfect when you need a quick answer inside your browser-based Claude interface without waiting on complex multi-step agent logic to resolve.

Setup guide

Set up LibreChat MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The LibreChat MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the LibreChat MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under librechat-mcp.

json

{
  "mcpServers": {
    "librechat-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by LibreChat. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect LibreChat now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about LibreChat MCP in Claude Desktop

Open your `claude_desktop_config.json` file and add the MCP Server configuration under the `mcpServers` block with your server URL. Restart Claude Desktop completely, and you will see the tools available via the hammer icon in your chat window.

Yes, you can connect this remote MCP Server to claude.ai by going to Settings, selecting Integrations, and pasting your remote server URL. This lets your web-based agent call completions and list models directly from the browser.

If your session expires, you need to run the `login` tool again to generate fresh access and refresh tokens. Claude Desktop stores these tokens locally to keep your connection to the LibreChat API active.

The `open_responses` tool accesses the raw Open Responses API for direct text generation. In contrast, `chat_completions` routes your prompts through specific LibreChat Agent IDs, applying their pre-configured system prompts and tools.

Your login tokens and chat payloads remain strictly within your local machine's memory and the secure Vinkius sandbox. No raw passwords or API keys are written to disk, and all communication with your LibreChat instance is encrypted in transit.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript