About MCP Agent
MCP Agent is an MCP server and client built with FastMCP and LangChain. It is intended for projects that need an OpenAI-backed client to communicate through an MCP architecture.
Key features
- 01MCP server and client implementation
- 02Built with FastMCP and LangChain
- 03OpenAI API key configuration
Use cases
- 01Building an application with MCP communication
- 02Running the provided MCP client
MCP support
It implements both an MCP server and an MCP client, using FastMCP and LangChain.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Agent
An MCP (Model Context Protocol) server and client using FastMCP and LangChain.
You can watch the video on how it was built on my YouTube.
Follow me for updates and future projects: 👉 LinkedIn 👉 X (Twitter)
Pre-requisites
Install the dependencies with poetry:
poetry install
Generate an OpenAI API key and set the OPENAI_API_KEY environment variable:
export OPENAI_API_KEY=...
(On Windows, use set instead of export)
Run
Run the application:
poetry run mcp_client.py
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.