{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_b65ertwyw439","handle":"qhung-cses-mcp","url":"https://wellknown.network/agents/qhung-cses-mcp","links":{"self":"https://wellknown.network/agents/qhung-cses-mcp/record.json","html":"https://wellknown.network/agents/qhung-cses-mcp","markdown":"https://wellknown.network/agents/qhung-cses-mcp/record.md","api":"https://wellknown.network/api/v1/agents/qhung-cses-mcp","status":"https://wellknown.network/api/v1/agents/qhung-cses-mcp/status","claim":"https://wellknown.network/agents/qhung-cses-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/qhung-cses-mcp/claim.json","badge":"https://wellknown.network/agents/qhung-cses-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/qhung-cses-mcp/history","tools":"https://wellknown.network/api/v1/agents/qhung-cses-mcp/tools"},"ard":{"identifier":"urn:air::server:qhung-cses-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"qhung-cses-mcp","summary":"An MCP server for browsing CSES problems, submissions, and submitting solutions","description":"# CSES MCP Server\n\n*Your AI assistant's gateway to [CSES](https://cses.fi) (Code Submission Evaluation System)* 🧩\n\n## 🤔 What is this?\n\n`cses-mcp` is a Python-based MCP (Model Context Protocol) server that lets\nan MCP-compatible client (like Claude Desktop or Claude Code) act on your\nbehalf on CSES: browsing problems, reading problem statements, submitting\nsolutions, and checking submission history/verdicts.\n\nAs far as I know, CSES has no public API, so all data access is via scraping authenticated HTML\npages and posting to existing web forms using your own session cookie.\n\n### Why?\n\nCSES is one of the best free problem sets for learning competitive\nprogramming, but working through it usually means a lot of manual tab-\nswitching: reading a statement, writing code elsewhere, coming back to\nsubmit, then digging through a verdict page to figure out what went wrong.\nThis project turns that whole loop into a conversation — ask an AI\nassistant to find you a problem, explain the statement, help you reason\nthrough an approach, submit your solution, and diagnose a wrong verdict,\nall without leaving the chat. The goal isn't to solve problems *for* you\n(though it can) — it's to make the feedback loop tight enough that you\nactually learn faster: get hints instead of full solutions when you want\nthem, understand *why* a submission got Wrong Answer or Time Limit\nExceeded, and use past-attempt history to see your own progress over time.\n\n---\n\n## 🚀 Quick Start\n\nPick whichever fits — Option A if you just want to use it, Option B if\nyou're editing the code.\n\n### Option A — Copy-paste (no local clone)\n\nPaste this straight into your MCP client config — `uvx` fetches and runs\nthe published package, no clone, no `uv sync`, no `.env` file to manage:\n\n```json\n{\n  \"mcpServers\": {\n    \"cses-mcp\": {\n      \"command\": \"uvx\",\n      \"args\": [\"qhung-cses-mcp@latest\"],\n      \"env\": {\n        \"PHPSESSID\": \"<your CSES session cookie>\"\n      }\n    }\n  }\n}\n```\n\nRequirements:\n- [`uv`](https://docs.as…","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:qhung-cses-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"content.writing","name":"Writing & Editing","confidence":0.802,"provenance":"derived"}],"categories":["content"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"qhung-cses-mcp","registry":"pypi","observedAt":"2026-11-03T23:22:44.140Z","publishedAt":"2026-07-06T10:34:42.111306Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"qhung-cses-mcp","url":"https://pypi.org/project/qhung-cses-mcp/","firstSeenAt":"2026-09-10T10:24:58.175Z","fetchedAt":"2026-11-03T23:20:32.064Z","normalizedAt":"2026-11-03T23:20:32.064Z"}]},"firstSeenAt":"2026-09-10T10:24:58.175Z","updatedAt":"2026-11-03T23:22:44.140Z"}