🦜 🔗 LangChain MCP Client

🦜🔗 LangChain Model Context Protocol (MCP) Client

Catalog onlyCatalog onlySTDIO

Overview

LangChain MCP Client is a tool that allows users to connect to Model Context Protocol (MCP) servers and utilize LangChain-compatible language models for various applications.

To use the LangChain MCP Client, install it via pip, configure your API keys and MCP servers in a .env file, and run the client from the command line.

Seamless connection to any MCP servers. - Flexibility to use any LangChain-compatible LLM. - Command-line interface for dynamic interactions.

Connecting to multiple MCP servers for enhanced model capabilities.
Utilizing various language models for different tasks.
Facilitating dynamic conversations through CLI interactions.

Add to your AI client

Use these steps to connect 🦜 🔗 LangChain MCP Client in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "langchain-mcp-client-datalayer": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-langchain-mcp-client-datalayer"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "langchain-mcp-client-datalayer": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-langchain-mcp-client-datalayer"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "langchain-mcp-client-datalayer": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-langchain-mcp-client-datalayer"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "langchain-mcp-client-datalayer": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-langchain-mcp-client-datalayer"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "langchain-mcp-client-datalayer": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-langchain-mcp-client-datalayer"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "langchain-mcp-client-datalayer": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-langchain-mcp-client-datalayer"
      ]
    }
  }
}

FAQ

What is the required Python version?

Python 3.11 or higher is required to run the LangChain MCP Client.

How do I configure the client?

Create a `.env` file with your API keys and configure the `llm_mcp_config.json5` file for LLM parameters and MCP servers.

Can I use it with any language model?

Yes, as long as the model is compatible with LangChain.

Developer tools