Codeforces Mcp
io.github.avinash111921Published by GitHub account avinash111921v0.1.0Updated Oct 29, 2026
Codeforces MCP server for competitive programming, upsolving, and automated stress testing.
Overview
Codeforces MCP server that lets an AI assistant fetch problems, review submission history, suggest upsolving targets, and run local stress tests.
- What you can do
- Fetch live Codeforces profile stats: ratings, ranks and recent verdict breakdowns
- Scrape full problem statements and exact sample test cases, bypassing Cloudflare
- Compile and run C++ or Python solutions locally against official sample inputs
- Run automated stress tests, comparing an optimized solution with a brute-force script and random generator to isolate minimal failing cases
- Queue and cache requests to stay within the Codeforces API rate limit
- When to use it
- Useful for competitive programmers who want an assistant to pull Codeforces problems and samples, review their submission history, pick upsolving targets, and debug solutions with local stress testing.
- Requirements
- Runs as a local process, launched with uvx from the codeforces-mcp PyPI package (Python tooling required). No accounts, API keys, environment variables or headers are declared. Network access to Codeforces is needed, and a local C++ or Python toolchain for compiling and running solutions.
Installation
In SourceWeft
- Open Codeforces Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Codeforces MCP Server
A Model Context Protocol (MCP) server for Codeforces competitive programming. This server enables AI coding assistants (like Claude, Cursor, and Cline) to autonomously fetch problem statements, analyze your submission history, recommend upsolving targets, and run automated local stress tests.
Features
- Profile & Stats: Fetch live user ratings, ranks, and recent verdict breakdowns.
- Problem Scraping: Bypasses Cloudflare to extract full problem descriptions and exact sample test cases.
- Local Sandbox: Compiles and executes C++ or Python solutions locally against official sample inputs.
- Automated Stress Testing: Isolates minimal failing test cases by running your optimized code against a brute-force script and a random generator.
- Rate-Limit Safe: Built-in queuing and caching ensures you never hit the Codeforces API 1-request-per-2-seconds limit.
Installation & Usage
You can run this server seamlessly using uvx without manual installation. Add the following configuration to your preferred AI IDE.
Cursor
Add this to your MCP configuration (Settings > Features > MCP):
Source: README.md at commit aa4f4ea
Tools
0Version history
1- v0.1.0LatestOct 29, 2026
Score
40% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.