botextractai/ai-mcp-server-client-fastmcp

The Model Context Protocol (MCP) server, implemented using FastMCP, is designed to facilitate seamless communication between clients and servers in the context of large language models (LLMs). FastMCP simplifies the setup of MCP servers by reducing the need for extensive boilerplate code and configuration. In this example, a local MCP server is created, and a LangChain Artificial Intelligence agent is used to interact with the server. The agent utilizes tools defined in the MCP server to gather and process information. The server-client communication is achieved through Python's standard input/output streams, while external servers would require alternative transport methods like Server-Sent Events (SSE) or WebSockets. The integration with YFinance allows the server to access financial data without the need for an API key, making it a versatile tool for financial queries. The example demonstrates the server's capability to answer complex questions about stock market data by leveraging the tools available in the MCP server.

python
mcp.run(transport='stdio')  # Tools defined via @mcp.tool() decorator

python
mcp.run(transport='sse', host="0.0.0.0", port=8000)  # Specify SSE endpoint

yaml
paths:
  /mcp:
    post:
      x-ms-agentic-protocol: mcp-streamable-1.0  # Copilot Studio integration

python
from mcp.server import FastMCP
app = FastMCP('demo')
@app.tool()
async def query(): ...