Langchain

Exposes LangChain agent capabilities via MCP with a scalable FastAPI backend on Google Cloud Run.

typescript

4

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You can run a production-ready MCP server that exposes a LangChain agent as a single MCP Tool, enabling clients to perform multi-step reasoning and tool execution through the Model Context Protocol. This server is built with FastAPI, deployable on Google Cloud Run, and designed for scalability, reliability, and easy integration with MCP-compliant clients.

How to use

To use this MCP server with your MCP client, first fetch the MCP manifest to discover available tools and input schemas. Then invoke the agent_executor tool to run complex queries that require multi-step reasoning and tool usage. You’ll interact with the server through standard MCP endpoints to start tasks, pass queries, and receive structured responses. If you need custom behavior for a single invocation, you can supply a system_instruction to tailor the agent’s prompt for that run.

How to install

Prerequisites include Python 3.11 or newer, an OpenAI API key, and a Google Cloud account for Cloud Run deployments. Optional dependencies include Docker for local testing.

Step 1: Clone the project repository and move into it.

Available tools

agent_executor

Executes a complex, multi-step reasoning task using LangChain, supporting an optional system_instruction to customize behavior per invocation.