io.github.richer-richard由 GitHub 账号 richer-richard 发布v1.1.0更新于 Nov 4, 2026
Search and sample 1,038,963 competition and benchmark math problems.
只读 MCP 服务器，基于本地约 104 万道竞赛与基准数学题数据库，支持全文检索、按条件随机抽样和读取完整题目记录。
Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。
参照 仓库 中的启动说明。
[Arquimedes — Open Database of Competition & Olympiad Mathematics]
[Listed on mcpservers.org] [Glama score] [CI] [Release] [Code license: MIT]
A structured, deduplicated database of competition and benchmark mathematics:
1,038,963 problems across 9 datasets, each with a normalized LaTeX statement,
calibrated Mohs difficulty (1.0 to 10.0), answer metadata, and solutions in a
uniform JSON schema (v2).
deepmath dataset, JSONL shards)1.0–10.0) populated across all 1,038,963 recordsuv (arquimedes CLI and arquimedes-mcp server)972,458 decontaminated train / 10,533 canonical eval)site/ ready for GitHub PagesPer-dataset category breakdowns and field notes: docs/datasets.md.
The source.collection field labels records that come from a named
competition or benchmark:
core): AHSME 1,810 · AMC 8 1,025 · AMC 10A 625 · AMC 10B 625 · AMC 10 50 · AMC 12A 625 · AMC 12B 625 · AMC 12 50 · AIME I 405 · AIME II 405 · AIME 255 · USAMO 153 · USA TST 45 · USA TSTST 48core): 156core): February 2,606 · November 1,072 · Invitational 65cemc): Gauss (Grade 7) 174 · Gauss (Grade 8) 166 · Pascal (Grade 9) 134 · Cayley (Grade 10) 150 · Fermat (Grade 11) 168aops): IMO Shortlist 102 · USAJMO 91 · Canadian MO 83 · APMO 28 · Putnam 7olympiadbench): 1,389math): 12,401Records in omnimath, deepmath, numina, and bigmath carry origin and domain labels in source.tags.
uv)arquimedes ships a zero-dependency Python package with both a fast CLI (arquimedes) and a Model Context Protocol server (arquimedes-mcp) backed by SQLite + FTS5 (with automatic JSONL shard fallback when SQLite is absent).
The package name is arquimedes-mcp. It does not contain the problems. Download them once from the Hugging Face dataset (about 1.3 GB of shards, then a lean index of about 0.8 GB):
That copy lives in the user data directory (~/Library/Application Support/arquimedes on macOS), so the next uvx run finds it.
Add to your mcp.json or claude_desktop_config.json when the shards are already in a checkout:
Exposed MCP tools (all read-only; arguments in docs/usage.md):
arquimedes_get_stats: dataset, category, competition, and solution countsarquimedes_search_problems: full-text search with category, dataset, competition, and min_mohs/max_mohs filtersarquimedes_sample_problems: uniform random draw among problems matching the filters, repeatable with a seedarquimedes_get_problem: full LaTeX statement, choices, answer, hints, solutions, and optional deepmath reasoning traces by idFrom 1.0.0 on, these interfaces only change in backward-compatible ways until a 2.0.0 release:
docs/schema.md: fields
are not removed or renamed, and their types do not changearquimedes CLI commands and flags, and their --json outputarquimedes buildArquimedesEngine methods get_stats, search, sample, and
get_problemNew fields, tools, flags, and data fixes can arrive in minor and patch
releases. Corrections to individual records (a wrong answer, a mislabeled
category) are data fixes, not breaking changes. Counts and difficulty.mohs
values can change as records are corrected; mohs is a calibration, not a
measured difficulty. Changes are listed in CHANGELOG.md.
For LLM post-training and RLVR (Reinforcement Learning with Verifiable Rewards), tools/export_splits.py (or uv run arquimedes splits) produces a decontaminated training set and a canonical evaluation benchmark:
splits/eval.jsonl.gz — 10,533 problems): math test split (4,974), omnimath (2,640), olympiadbench (1,389), core 2023+ contests (931), aops (311), and cemc 2023+ contests (288).splits/train.jsonl.gz — 972,458 problems): filters out 46,057 unverifiable records and strips 9,915 near-duplicate benchmark leaks detected via 5-gram token shingle overlap across numina, bigmath, core, math, deepmath, and cemc.Read a problem directly from a shard with the Python standard library:
Query SQLite + FTS5 directly:
docs/schema.md: full v2 record reference, shard format, SQLite + FTS5 schema, LaTeX convention, image storedocs/usage.md: CLI, MCP server, SQL & FTS5 queries, reasoning traces, decontaminated splitsdocs/datasets.md: per-dataset contents, field notes, category distributions, deduplication rules, and upstream licensesCode in arquimedes/, tools/, and site/ is MIT. The Mohs calibration, the category labels assigned by this project, and data/index.json are CC BY 4.0. Problem statements, solutions, answers, and diagrams are not relicensed; the upstream terms are in docs/datasets.md. A Hugging Face copy keeps every record and stamps the holder's notice on it: richard01172000/arquimedes. See LICENSE.
来源：README.md，提交 d142f84
Database Statistics
Summarize what the Arquimedes math problem database holds: the problems this server can search (it is running without its SQLite index, so that is only part of the full corpus), with problem counts by dataset, category, and competition, and written-solution counts by kind. Call it first to learn which category, dataset, and competition values exist before filtering arquimedes_search_problems or arquimedes_sample_problems. Takes no arguments.
无需输入参数。
Search Math Problems
Find problems by keyword in the competition and olympiad math problems this server can scan (it is running without its SQLite index; call arquimedes_get_stats for exact coverage). Full-text search returns problems whose statement or title contains all the query words: a topic, a theorem name such as 'Cauchy-Schwarz', or a LaTeX fragment. Optional filters narrow by category, dataset, competition, and Mohs difficulty (1.0 to 10.0). Results are summaries (id, title, competition, year, difficulty, answer, statement) without solutions; pass an id to arquimedes_get_problem for solutions and hints. To get random problems instead of keyword matches, use arquimedes_sample_problems.
limitquery必填datasetcategorymax_mohsmin_mohscompetitionSample Math Problems
Draw random problems from the competition and olympiad math problems this server can scan (it is running without its SQLite index; call arquimedes_get_stats for exact coverage), uniformly among those matching optional filters: category, dataset, competition, contest year, Mohs difficulty range (1.0 to 10.0), multiple-choice only, or with a diagram. Use it to build practice sets, mock contests, or evaluation samples; pass the same seed to repeat a draw. Results are summaries without solutions; pass an id to arquimedes_get_problem for solutions. To find problems about a specific topic or keyword, use arquimedes_search_problems.
seedyearlimitdatasetcategorymax_mohsmin_mohscompetitionhas_choiceshas_diagramGet Math Problem by ID
Fetch one problem by its id, as returned by arquimedes_search_problems or arquimedes_sample_problems (e.g. 'prob.ahsme-1950-p10', 'prob.numina-000369'). Returns the full record: LaTeX statement, answer choices, answer, written solutions with progressive hints, difficulty, source, and diagram references. Ids cannot be guessed; an unknown id returns an error, so discover ids with search or sample first.
problem_id必填include_tracesinclude_solutions已满足适用检查项的 80%
该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。
请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。
请在仓库或注册中心条目中声明许可证。
uvx arquimedes-mcp fetch{ "mcpServers": { "arquimedes": { "command": "uvx", "args": ["arquimedes-mcp"] } }}uvx --from arquimedes-mcp arquimedes statsuvx --from arquimedes-mcp arquimedes search "Cauchy-Schwarz" --min-mohs 7.0 -n 5# Build the local 1.7 GB SQLite + FTS5 database (~50 seconds)uv run arquimedes build# or a 0.8 GB index that reads solutions from the shardsuv run arquimedes build --lean
# Show corpus summaryuv run arquimedes stats
# Sub-20ms full-text search across 1,038,963 problemsuv run arquimedes search "Cauchy-Schwarz" --min-mohs 7.0 -n 5
# Sample calibrated problems by competition, category, or Mohs difficultyuv run arquimedes sample --competition IMO --category geometry -n 3
# Inspect a full problem record with choices, answer, hints, and proofuv run arquimedes show prob.ahsme-1950-p10{ "mcpServers": { "arquimedes": { "command": "uv", "args": ["--directory", "/path/to/arquimedes", "run", "arquimedes-mcp"] } }}uv run arquimedes splits --out-dir splits/import gzip, json
with gzip.open("problems/core/shard-00000.jsonl.gz", "rt", encoding="utf-8") as fh: prob = json.loads(fh.readline())
print(prob["title"], "Mohs:", prob["difficulty"]["mohs"])print(prob["statement"]) # raw LaTeX with \( \) delimitersprint(prob["answer"]) # {'letter': 'd', 'value': '3+\\sqrt6'}print(prob["solutions"][0]["text"][:200])SELECT p.id, p.title, p.difficulty_mohs, p.answer_valueFROM problems_fts fJOIN problems p ON p.rowid = f.rowidWHERE problems_fts MATCH '"pigeonhole"' AND p.difficulty_mohs BETWEEN 5.0 AND 8.5LIMIT 10;problems/<dataset>/shard-*.jsonl.gz gzipped JSON Lines, one v2 problem record per lineimages/<hash>.svg, images/<hash>.jpg 1,219 content-addressed diagram filesdata/index.json summary index (counts by dataset, category, competition)data/problems.sqlite queryable SQLite + FTS5 database (build locally)arquimedes/ uv-installable CLI and MCP server packagesite/ minimalistic interactive web explorer (GitHub Pages)tools/ converters, shard normalizer, split exporter, DB builderdocs/ schema, usage, and dataset documentation