How to Use the LibreChat MCP in Cursor

Q: How do I add the LibreChat server to my Cursor configuration?

Create a .cursor/mcp.json file in your project root or your home directory, and define the MCP Server under the mcpServers key. Once saved, Cursor automatically starts the server, and the tools will be ready in Agent mode.

Q: What should I do if LibreChat returns an authentication error in Cursor?

Run the login tool inside Cursor to refresh your credentials. This generates new access and refresh tokens, resolving any expired session issues with your self-hosted LibreChat API.

Q: Can I run this MCP Server globally across all my Cursor projects?

Yes, adding the configuration to your global /.cursor/mcp.json file makes the tools available in every project you open. Your active LibreChat login session will persist across these different workspaces.

Generate code using live LibreChat model completions and custom agents directly inside Cursor.

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 Cursor

Create your Vinkius account to connect LibreChat to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject live LibreChat completions into your Cursor code

The `chat_completions` tool brings your self-hosted LibreChat Agent IDs directly into the Cursor Composer and chat sidebar. Cursor uses these endpoints to generate code based on the exact system instructions and custom contexts you defined in your LibreChat dashboard. Instead of writing code against placeholder APIs, your editor calls your actual backend agents to draft functions. This means the code generated by Cursor matches the specific behavior and constraints of your proprietary LibreChat deployment.

Query your active model registry from the editor

The `list_models` tool queries your LibreChat instance to fetch all active models and custom agents currently available. Cursor reads this list dynamically, allowing you to switch between different backend LLMs without leaving your active workspace. By integrating this MCP Server into your `.cursor/mcp.json` file, your editor stays synced with backend changes. If your team adds a new fine-tuned model to LibreChat, it immediately shows up in your Cursor environment.

Secure your editor sessions with native login

The `login` tool handles authentication directly from Cursor, retrieving the required access and refresh tokens to communicate with your self-hosted API. This prevents you from hardcoding sensitive API keys in your project files or global environment variables. Once authenticated, you can use `open_responses` to run lightweight text generation tasks without the overhead of heavy agent pipelines. This is ideal for generating quick docstrings or commit messages directly within your editor's terminal or chat pane.

Setup guide

Set up LibreChat MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the LibreChat MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent LibreChat transactions." If the MCP tools are loaded correctly, Cursor will call the LibreChat tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Create a `.cursor/mcp.json` file in your project root or your home directory, and define the MCP Server under the `mcpServers` key. Once saved, Cursor automatically starts the server, and the tools will be ready in Agent mode.

Yes, this MCP integration maps specific Agent IDs from LibreChat to Cursor. When you prompt the editor in Agent mode, it can trigger those specific agents to write or refactor code.

Run the `login` tool inside Cursor to refresh your credentials. This generates new access and refresh tokens, resolving any expired session issues with your self-hosted LibreChat API.

Yes, adding the configuration to your global `~/.cursor/mcp.json` file makes the tools available in every project you open. Your active LibreChat login session will persist across these different workspaces.

No, your authentication tokens and generated code snippets are handled entirely within Cursor's local runtime and the secure Vinkius isolate. Your credentials are never shared with third-party tracking services or external model providers.

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