Codeforces MCP Server

A Model Context Protocol (MCP) server that provides a comprehensive set of tools for interacting with the Codeforces competitive programming platform. Built with FastMCP and Python.

This server exposes tools that can be used by any MCP-compatible client (e.g., Claude Desktop, Cline, etc.) to fetch user profiles, compare users, search problems, generate practice plans, and more.

Features

Installation

Prerequisites

• Python 3.10+
• pip (Python package manager)

Setup

# Clone the repository
git clone https://github.com/spr7a/cf-mcp.git
cd cf-mcp

# Install dependencies
pip install fastmcp httpx

Usage

Running the Server

python test.py

The server runs on stdio transport by default, making it compatible with MCP clients.

Configuring with Claude Desktop / Cline

Add the following to your MCP settings configuration file (e.g., ~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json):

{
  "mcpServers": {
    "codeforces": {
      "command": "python",
      "args": ["/path/to/cf-mcp/test.py"]
    }
  }
}

Example Queries

Once connected, you can ask your MCP client questions like:

• "What is tourist's Codeforces profile?"
• "Compare tourist and petr side by side."
• "Find me DP problems rated 1600-1800."
• "Get the full statement for problem 4A."
• "Generate a practice plan for reikc."
• "Give me a random problem for reikc."
• "What unsolved problems does reikc have from recent contests?"
• "What did reikc solve recently?"

Project Structure

cf-mcp/
├── test.py                  # Main MCP server entry point (FastMCP)
├── tools/
│   ├── get_user.py          # Fetch & parse user profile data
│   ├── compare_user.py      # Compare two users side-by-side
│   ├── get_problemlist.py   # Search problemset with filters
│   ├── get_problem.py       # Fetch full problem statement
│   ├── get_practice.py      # Generate practice plan from weak topics
│   ├── get_random_problem.py# Random problem suggestion
│   ├── get_upsolve.py       # Upsolve recommendations from recent contests
│   ├── get_status.py        # Submission status & history
│   └── problems.py          # Shared problem-fetching utilities
└── README.md

How It Works

The entire tool suite is powered by the official Codeforces API, which acts as the backbone for all data operations. To ensure lightning-fast performance, the server uses Python's httpx library to issue asynchronous, non-blocking network calls, allowing multiple requests to run in parallel instead of waiting for each one sequentially.

Dependencies

• fastmcp — MCP server framework
• httpx — Async HTTP client

License

MIT