加载中…
Airtight math for AI agents: 3.68M-doc theorem search + numeric/Lean verification. No LLM, no key.
io.github.Archerkattri/mathlas 是 ChatHome Skills 收录的 MCP 条目，来源为 Official MCP Registry，质量分 67/100。 作为 Model Context Protocol 服务器，它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具，让 agent 的能力超出模型内置范围。 该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录，每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。 质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势，完整算法说明见来源页。安装命令已列于上方，可直接复制使用。 在将 io.github.Archerkattri/mathlas 加入生产 agent 工作流前，请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。
uvx mathlas-mcp==1.5.0运行此命令前，请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-07-02T02:49:38.314229Z",
"publishedAt": "2026-07-02T02:49:38.314229Z",
"statusChangedAt": "2026-07-02T02:49:38.314229Z"
}
},
"server": {
"name": "io.github.Archerkattri/mathlas",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json",
"version": "1.5.0",
"packages": [
{
"version": "1.5.0",
"transport": {
"type": "stdio"
},
"identifier": "mathlas-mcp",
"runtimeHint": "uvx",
"registryType": "pypi",
"registryBaseUrl": "https://pypi.org",
"environmentVariables": [
{
"name": "MATHLAS_SEED",
"description": "Set to 1 to force the lightweight built-in seed corpus and never load the multi-GB prebuilt index (fast cold start)."
},
{
"name": "MATHLAS_INDEX",
"description": "Path to a prebuilt index .npz to serve for search_existing_math (optional; the seed corpus is used when absent)."
}
]
}
],
"repository": {
"url": "https://github.com/Archerkattri/mathlas",
"source": "github"
},
"description": "Airtight math for AI agents: 3.68M-doc theorem search + numeric/Lean verification. No LLM, no key."
}
}