Codeforces MCP server

@pipeworx/codeforces

Codeforces public read API MCP — competitive programming users, contests, problems, submissions. Keyless.

Part of Pipeworx — an MCP gateway connecting AI agents to 1679+ live data sources.

Tools

• user(handles[]) — profile(s) by handle (up to 10k)
• user_rating(handle) — full rating history for a user
• user_status(handle, count?) — recent submissions for a user
• contest_list(gym?) — all contests (regular or gym)
• conteststandings(contestid, handles?, from?, count?) — final scoreboard + problem list for one contest
• problemset(tags?, problemset_name?) — problemset + recent submissions stats
• recentactions(maxcount?) — recent global actions feed
• blogentryview(blog_id) — full blog entry by id

Standings paging is done here, not upstream

Codeforces rejects from, count and handles on public standings — it answers HTTP 400 with "Non-gym contest standings for non-admin users are available only via anonymous GET requests with no extra parameters". The only request it accepts is the bare ?contestId=, which returns the entire scoreboard (2.7 MB for contest 1000, 14 MB for contest 2000).

So contest_standings streams that response and slices it here: from/count page the rows and handles filters them, with the same meaning they had before. Nothing is held in memory beyond the window you asked for. Two consequences worth knowing:

response carries hasmore: true instead of totalrows — the participant count is genuinely unknown at that point. Ask for a window past the end of the scoreboard, or pass handles, and you get total_rows.

• Without a handles filter the read stops as soon as your window is full, so the

authenticated Codeforces account and this pack is keyless, so it returns {found: false, reason: "gymcontestrequirescodeforcesaccount"} rather than an error.

• Gym contests are not available at all. Codeforces serves gym standings only to an

Data source

https://codeforces.com/api/

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "codeforces": {
      "url": "https://gateway.pipeworx.io/codeforces/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/codeforces/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — askpipeworx, discovertools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1679+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/codeforces_user \
  -H 'Content-Type: application/json' \
  -d '{"handles":["tourist"]}'

Shortened. The full README is on GitHub.