MCP Tools Usage From LangChain / Example in Python

This simple Model Context Protocol (MCP) client demonstrates the use of MCP server tools by LangChain ReAct Agent.

It leverages a utility function convert_mcp_to_langchain_tools() from langchain_mcp_tools.
This function handles parallel initialization of specified multiple MCP servers and converts their available tools into a list of LangChain-compatible tools (list[BaseTool]).

Google GenAI's gemini-2.0-flash is used as the LLM. For convenience, code for OpenAI's and Anthropic's LLMs are also included and commented out.

A bit more realistic (conversational) MCP Client is available here

A typescript equivalent of this MCP client is available here

Prerequisites

• Python 3.11+
• [optional] uv (uvx) installed to run Python package-based MCP servers
• [optional] npm 7+ (npx) to run Node.js package-based MCP servers
• LLM API keys from OpenAI, Anthropic, and/or Google GenAI as needed

Usage

1. Install dependencies:

   make install

2. Setup API key:

   cp .env.template .env

   • Update .env as needed.
   • .gitignore is configured to ignore .env to prevent accidental commits of the credentials.

3. Run the app:

   make start

   It takes a while on the first run.

Simple Exapmle Code for Streamable HTTP Authentiocation

A simple example of showing how to implement an OAuth client provider and use it with the langchain-mcp-tools library can be found in src/streamable_http_oauth_test_client.py.

For testing purposes, a sample MCP server with OAuth authentication support that works with the above client is provided in src/streamable_http_oauth_test_server.py.

You can run the server with make run-streamable-http-oauth-test-server and the client with make run-streamable-http-oauth-test-client.