langchain-mcp
About
Model Context Protocol tool support for LangChain
Details
- Author
- rectalogic
- GitHub stars
- 205
- Downloads
- 738
- Categories
- AI
Jump to
- Integrates MCP tool calling into LangChain workflows
- Exposes an async MCPToolkit class for session management
- Automatically converts MCP tools into BaseTool objects
- Works with any MCP server that communicates over a ClientSession
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
langchain-mcpCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Create a langchain_mcp.MCPToolkit by passing it an mcp.ClientSession, then call await toolkit.initialize() followed by toolkit.get_tools() to retrieve a list of LangChain BaseTools. The toolkit handles the MCP client‑server lifecycle and tool discovery.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"langchain-mcp": {
"langchain-mcp": {
"command": "uv",
"args": [
"run",
"tests/demo.py",
"Read and summarize the file ./LICENSE"
]
}
}
}
}McpServers
{
"langchain-mcp": {
"command": "uv",
"args": [
"run",
"tests/demo.py",
"Read and summarize the file ./LICENSE"
]
}
}langchain-mcp
Note: langchain now has a more official implementation langchain-mcp-adapters
Model Context Protocol tool calling support in LangChain.
Create a langchain_mcp.MCPToolkit with an mcp.ClientSession,
then await toolkit.initialize() and toolkit.get_tools() to get the list of langchain_core.tools.BaseTools.
Example:
https://github.com/rectalogic/langchain-mcp/blob/8fa8445a24755bf91789f52718c32361ed916f46/tests/demo.py#L34-L43
Demo
You can run the demo against Groq llama-3.1-8b-instant:
``sh-session``
$ export GROQ_API_KEY=xxx
$ uv run tests/demo.py "Read and summarize the file ./LICENSE"
Secure MCP Filesystem Server running on stdio
Allowed directories: [ '/users/aw/projects/rectalogic/langchain-mcp' ]
The file ./LICENSE is a MIT License agreement. It states that the software is provided "as is" without warranty and that the authors and copyright holders are not liable for any claims, damages, or other liability arising from the software or its use.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
