Summary
Connects Claude to the Codeforces competitive programming platform through eight read-only API tools. You can pull user profiles and rating histories, browse recent submissions, list contests and their standings, search the problemset with optional tag filters, and view blog entries. Handles batch lookups for up to 10,000 users at once. Built on the Pipeworx gateway, so you can either connect to this standalone server or use the full gateway that includes 673+ other data sources. Useful if you're building coding interview prep tools, analyzing competitive programming trends, or just want Claude to look up contest results and problem statistics without leaving the conversation.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Tools
Public tool metadata for what this MCP can expose to an agent.
11 tools
get_user_statsFetch complete user profile, rating, rank, and solve counts.1 params
Fetch complete user profile, rating, rank, and solve counts.
Parameters* required
handlestringThe codeForces user handle (e.g., tourist)
get_recent_activityFetch complete the most recently solved Problem , Contest , Points , Link , Tags, by the user.1 params
Fetch complete the most recently solved Problem , Contest , Points , Link , Tags, by the user.
Parameters* required
handlestringThe Codeforces user handle
get_tag_breakdownFetch all accepted submissions for a user and calculate how many unique problems they have solved for each topic tag (e.g., dp, math, greedy).1 params
Fetch all accepted submissions for a user and calculate how many unique problems they have solved for each topic tag (e.g., dp, math, greedy).
Parameters* required
handlestringThe Codeforces user handle
get_best_contest_rankFetch the user's best ever performance (highest rank) in a single Codeforces contest.1 params
Fetch the user's best ever performance (highest rank) in a single Codeforces contest.
Parameters* required
handlestringThe Codeforces user handle
analyze_weak_topicsIdentify underperforming tags and suggest focus areas based on the user's lowest solve counts.1 params
Identify underperforming tags and suggest focus areas based on the user's lowest solve counts.
Parameters* required
handlestringThe Codeforces user handle
get_rating_historyFetch the user's rating changes over time, including their latest contest performances and overall rating trajectory.1 params
Fetch the user's rating changes over time, including their latest contest performances and overall rating trajectory.
Parameters* required
handlestringThe Codeforces user handle
get_virtual_contestSuggest custom practice virtual contests based on the user's rating, excluding ones they have already competed in.1 params
Suggest custom practice virtual contests based on the user's rating, excluding ones they have already competed in.
Parameters* required
handlestringThe Codeforces user handle
get_recommend_problemsSmart problem suggestions based on the user's current rating and their weakest topic areas.1 params
Smart problem suggestions based on the user's current rating and their weakest topic areas.
Parameters* required
handlestringThe Codeforces user handle
get_search_problemsSearch the Codeforces problem set by specific tags, minimum rating, and maximum rating.4 params
Search the Codeforces problem set by specific tags, minimum rating, and maximum rating.
Parameters* required
limitnumberNumber of problems to return (default 5, max 20)
maxRatingnumberMaximum difficulty rating (e.g., 1600)
minRatingnumberMinimum difficulty rating (e.g., 1200)
tagsarrayList of topic tags to search for (e.g., ['dp', 'graphs'])
get_problem_statsFetch deep statistics for a specific Codeforces problem, including its rating, global solve count, and topic tags.2 params
Fetch deep statistics for a specific Codeforces problem, including its rating, global solve count, and topic tags.
Parameters* required
contestIdnumberThe Codeforces contest ID (e.g., 2044)
indexstringThe problem index letter (e.g., 'E' or 'A1')
compare_usersCompare two Codeforces users side-by-side, including their ratings, total solves, problem overlap, and unique solves.2 params
Compare two Codeforces users side-by-side, including their ratings, total solves, problem overlap, and unique solves.
Parameters* required
handle1stringThe first Codeforces user handle
handle2stringThe second Codeforces user handle
@pipeworx/codeforces
Codeforces public read API MCP — competitive programming users, contests, problems, submissions. Keyless.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
Tools
user(handles[])— profile(s) by handle (up to 10k)user_rating(handle)— full rating history for a useruser_status(handle, count?)— recent submissions for a usercontest_list(gym?)— all contests (regular or gym)contest_standings(contest_id, handles?, from?, count?)— standings + problems for one contestproblemset(tags?, problemset_name?)— problemset + recent submissions statsrecent_actions(max_count?)— recent global actions feedblog_entry_view(blog_id)— full blog entry by id
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 — ask_pipeworx,
discover_tools, 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 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Codeforces data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →