Enables AI assistants to fetch competitive programming problems, analyze user statistics, and perform automated local stress testing.
Also known as avinash111921/codeforces-mcp, codeforces-mcp-avinash
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.1.0
- Last commit
- Oct 28, 2026
- License
- —
What is Codeforces MCP?
Codeforces enables AI assistants to fetch competitive programming problems, analyze user statistics, and perform automated local stress testing.
Summary generated from the project's README
About Codeforces MCP server
Competitive programmers can use this tool to integrate Codeforces data directly into AI coding assistants like Claude, Cursor, or Cline. It allows an AI to fetch full problem descriptions and sample test cases by bypassing Cloudflare protections. Users can also retrieve live profile statistics, including current ratings, ranks, and recent verdict breakdowns, to help the assistant recommend specific upsolving targets based on submission history.
Beyond data retrieval, the server provides a local sandbox for executing C++ or Python solutions against official sample inputs. It includes an automated stress testing feature that identifies minimal failing test cases by comparing optimized code against a brute-force script and a random generator. The server is designed to respect the Codeforces API limit of one request every two seconds through built-in queuing and caching. You can set it up in your IDE using the uvx command.
What you can do with it
- 1Extract problem details for solvingHave the assistant pull the complete problem statement and sample inputs directly from the platform.
- 2Debug code with automated stress testingRequest the assistant to find the smallest possible input that causes your solution to fail.
- 3Verify solutions locallyRun your C++ or Python code against official sample inputs to ensure correctness before submitting.
Written from the project's README. Every use case is checked against a quote from it.
How to install Codeforces MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Codeforces MCP in Claude Code
$ claude mcp add codeforces-mcp -- uvx codeforces-mcp-avinashInstall Codeforces MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"codeforces-mcp": {
"command": "uvx",
"args": [
"codeforces-mcp-avinash"
]
}
}
}Install Codeforces MCP in VS Code
.vscode/mcp.json
{
"servers": {
"codeforces-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"codeforces-mcp-avinash"
]
}
}
}Install Codeforces MCP in VS Code CLI
$ code --add-mcp '{"name":"codeforces-mcp","type":"stdio","command":"uvx","args":["codeforces-mcp-avinash"]}'Install Codeforces MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"codeforces-mcp": {
"command": "uvx",
"args": [
"codeforces-mcp-avinash"
]
}
}
}Install Codeforces MCP in Codex
$ codex mcp add codeforces-mcp -- uvx codeforces-mcp-avinashInstall Codeforces MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.codeforces-mcp] command = "uvx" args = ["codeforces-mcp-avinash"]
Install Codeforces MCP in Gemini CLI
$ gemini mcp add -s user codeforces-mcp uvx -- codeforces-mcp-avinashInstall Codeforces MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"codeforces-mcp": {
"command": "uvx",
"args": [
"codeforces-mcp-avinash"
]
}
}
}Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work · What to fix for more points
- Source repository linked and reachableavinash111921/codeforces-mcp is public and reachablegithub.com/avinash111921/codeforces-mcp ↗Pass
- Package names this repository as its sourcecodeforces-mcp-avinash names avinash111921/codeforces-mcp as sourcepypi.org/project/codeforces-mcp-avinash/ ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-10-28github.com/avinash111921/codeforces-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from codeforces-mcp-avinashPass
- No critical advisory in the package or its dependencies44 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubCodeforces 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):
{
"mcpServers": {
"codeforces-mcp": {
"command": "uvx",
"args": ["codeforces-mcp"]
}
}
}
Codeforces MCP questions
How do I add Codeforces MCP to Claude Code?
Run claude mcp add codeforces-mcp -- uvx codeforces-mcp-avinash in your terminal. Add --scope user to make it available in every project.
How do I add Codeforces MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How can I run this server?
You can run the server using the uvx command without needing a manual installation.
Does the server handle Codeforces API rate limits?
Yes, it includes built-in queuing and caching to respect the 1-request-per-2-seconds limit.
Can the server extract problem details?
The server can bypass Cloudflare to scrape full problem descriptions and sample test cases.