How to Use the LibreChat MCP in VS Code Copilot

Q: How do I share my LibreChat tools with my team in VS Code Copilot?

Create a .vscode/mcp.json file in your repository root and add the MCP Server configuration. When team members open the project in VS Code 1.96+, Copilot will automatically load the tools for them.

Q: Can I use LibreChat agents for inline code completions in VS Code Copilot?

The chatcompletions tool is designed for conversational tasks in the Copilot Chat panel. You can ask Copilot to use a specific LibreChat Agent ID to explain, refactor, or write code blocks.

Q: How do I log in to my LibreChat server from VS Code Copilot?

Use the login tool inside the Copilot Chat interface to input your credentials. This retrieves the necessary access tokens, which are stored securely to authenticate all subsequent requests.

Share custom LibreChat agents and completions across your entire team using VS Code Copilot.

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 VS Code Copilot

Create your Vinkius account to connect LibreChat to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Call LibreChat agents inside VS Code Copilot Chat

The `chat_completions` tool lets you run custom LibreChat Agent IDs directly within your VS Code Copilot Chat panel. By committing an MCP configuration file to your repository, your entire engineering team gains instant access to the same tools. This setup ensures that everyone on the team generates code using the identical backend configurations and rules defined in LibreChat. Copilot routes your chat inputs directly to the specified Agent ID, keeping your development standards uniform.

Sync available models across team workspaces

The `list_models` tool pulls the current list of active models and agents from your shared LibreChat instance. VS Code Copilot uses this list to verify which endpoints are online before sending generation requests. When you configure this MCP Server globally or per-workspace, Copilot adapts to backend updates automatically. If an administrator updates the available models on your LibreChat server, your editor's tools update without requiring manual config edits.

Authenticate securely within your active workspace

The `login` tool manages your credentials by obtaining secure access and refresh tokens directly from your LibreChat server. This ensures that team members authenticate individually, maintaining audit logs on your self-hosted backend. After logging in, Copilot can also use `open_responses` for fast, direct text generation tasks. This allows developers to quickly generate unit tests or documentation without triggering complex, multi-agent workflows.

Setup guide

Set up LibreChat MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the LibreChat MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the LibreChat tools listed. Try asking: "List my recent LibreChat transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Create a `.vscode/mcp.json` file in your repository root and add the MCP Server configuration. When team members open the project in VS Code 1.96+, Copilot will automatically load the tools for them.

The `chat_completions` tool is designed for conversational tasks in the Copilot Chat panel. You can ask Copilot to use a specific LibreChat Agent ID to explain, refactor, or write code blocks.

Use the `login` tool inside the Copilot Chat interface to input your credentials. This retrieves the necessary access tokens, which are stored securely to authenticate all subsequent requests.

Yes, as long as your local VS Code environment can route traffic to your self-hosted LibreChat instance, the tools will function correctly. The local stdio transport handles the connection without issues.

Your access and refresh tokens are stored in VS Code's native secure credential storage. They are never committed to your Git repository or exposed to outside telemetry services.

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