Skip to main content
Glama
AtharvaJadhav

MCP Agent

MCP Agent

A production-ready research agent using the Model Context Protocol (MCP), FastAPI, and Serper web search.

Features

  • Async MCP server with web search tool (Serper API)

  • FastAPI client for HTTP access

  • Full test suite with pytest and Serper API mocking

Related MCP server: WebQuest MCP

Setup

  1. Clone the repo

  2. Install dependencies:

    pip install -r requirements.txt
  3. Set your Serper API key:

    • Create a .env file:

      SERPER_API_KEY=your_real_serper_api_key
      REQUEST_TIMEOUT=30
      MAX_RESULTS=20
      LOG_LEVEL=INFO

Usage

  • Start FastAPI client (runs MCP server as subprocess):

    python -m client.fastapi_client
  • POST /search for web search:

    { "query": "search term", "max_results": 10 }
  • GET /health for health check

Testing

  • Run all tests:

    pytest tests/test_e2e.py -v
  • Run integration test (real Serper API):

    pytest -m integration tests/test_e2e.py

MIT License

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    A production-ready Model Context Protocol server that brings AI-powered web search directly into development environments, providing intelligent search results with proper citations in Claude Desktop, Cursor, or any MCP-compatible client.
    79 npm
    23
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    A self-contained web-research MCP server that lets local LLM agents search, fetch, and synthesize web content using tools like web_search, web_fetch, and web_research.
    2
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI agents to perform web research in one tool call by searching, fetching and cleaning full pages, and ranking cited passages. Provides web_research, web_fetch, web_search, and status tools for MCP clients.
    1
    MIT