{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_m7n36xtzzbbz","handle":"chinese-corpus-mcp","url":"https://wellknown.network/agents/chinese-corpus-mcp","links":{"self":"https://wellknown.network/agents/chinese-corpus-mcp/record.json","html":"https://wellknown.network/agents/chinese-corpus-mcp","markdown":"https://wellknown.network/agents/chinese-corpus-mcp/record.md","api":"https://wellknown.network/api/v1/agents/chinese-corpus-mcp","status":"https://wellknown.network/api/v1/agents/chinese-corpus-mcp/status","claim":"https://wellknown.network/agents/chinese-corpus-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/chinese-corpus-mcp/claim.json","badge":"https://wellknown.network/agents/chinese-corpus-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/chinese-corpus-mcp/history","tools":"https://wellknown.network/api/v1/agents/chinese-corpus-mcp/tools"},"ard":{"identifier":"urn:air::server:chinese-corpus-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"chinese-corpus-mcp","summary":"中华版本语料库平台官方 MCP Server（Python 版）— chunk_search / deep_research / book_search（默认一把 API Key，数据集在平台后台切换）","description":"# chinese-corpus-mcp\n\n中文语料平台的官方 MCP（Model Context Protocol）服务器（Python 版）。接入后，你的 AI 助手（Claude、Cursor、其他 MCP 客户端）可以直接检索平台授权语料、发起深度研究、查询全平台图书元数据。\n\n与 npm 版 [`@chinese-corpus/mcp-server`](https://www.npmjs.com/package/@chinese-corpus/mcp-server) 是同一产品的两种语言实现，功能完全对等：**二选一安装即可**——机器上有 Python 用本包（uvx 直跑，无需安装 Node.js），有 Node.js 用 npm 版。\n\n## 五个工具\n\n| 工具 | 作用 | 计费 |\n| --- | --- | --- |\n| `chunk_search` | 在当前数据集内做语义+关键词混合检索，返回带引用四要素（书名/作者/出版社/章节）的图书片段 | 每次调用扣积分（数据集单价） |\n| `deep_research` | 提交深度研究任务并阻塞等待结构化报告（子问题/结论/证据/引用） | 每次任务扣积分 |\n| `deep_research_status` | 按 taskId 查询任务状态/进度/报告（超时后的取回通道） | 不扣积分（状态查询） |\n| `book_search` | 检索全平台图书元数据（CIP 在版编目），与 Key 绑定的数据集无关 | 免费 |\n| `get_service_context` | 只读自查：当前 Key 绑定了哪个数据集 | 不扣积分 |\n\n**数据集范围由你的 API Key 在平台侧决定**：工具参数、环境变量、配置文件里都没有（也不允许有）\"选数据集\"的开关。要换数据集，去平台网站「用户中心 → API Key 管理」切换当前绑定即可，下一次调用立即生效，MCP 服务器无需重启、无需改配置。\n\n## 安装（推荐：一句话让 AI 助手帮你装）\n\n需要 Python 3.11+ 与 [uv](https://docs.astral.sh/uv/)（`curl -LsSf https://astral.sh/uv/install.sh | sh`）。把下面这段话原样发给你的 AI 助手（Claude / Cursor 等），它会帮你完成安装和配置：\n\n> 请帮我安装中文语料平台的 MCP 服务器：在终端运行 `uvx chinese-corpus-mcp --help` 确认可用（需要 Python 3.11+ 与 uv），然后把它注册为 MCP 服务器（命令 `uvx`，参数 `chinese-corpus-mcp`，环境变量 `CHINESE_CORPUS_API_KEY`，值我会单独提供）。全部工具（chunk_search / deep_research / deep_research_status / book_search / get_service_context）都启用，不需要任何启动参数。\n\n不想用 AI 助手？也可以先安装再配置：`pipx install chinese-corpus-mcp`（或 `pip install chinese-corpus-mcp`），然后命令填 `chinese-corpus-mcp`。uvx 形态免安装、卸载即删配置，对系统侵入最小。\n\n## 手动配置\n\n### Claude Desktop / 标准 MCP 客户端（单服务器）\n\n在 MCP 配置文件（如 `claude_desktop_config.json`）中加入：\n\n```json\n{\n  \"mcpServers\": {\n    \"chinese-corpus\": {\n      \"command\": \"uvx\",\n      \"args\": [\"chinese-corpus-mcp\"],\n      \"env\": {\n        \"CHINESE_CORPUS_API_KEY\": \"ck_你的APIKey\"\n      }\n    }\n  }\n}\n```\n\n### 环境变量\n\n| 变量 | 必填 | 说明 |\n| --- | --- | --- |\n| `CHINESE_CORPUS_API_KEY` | 是 | 平台 API Key（形如 `ck_...`），在平台「用户中心 → API Key 管理」创建；只在创建时完整展示一次 |\n| `CHINESE_CORPUS_API_BASE_URL` | 否 | 平台 API 地址，默认 `http://10.25.2.15`（平台内网入口，通常无需修改）；仅当平台方另行提供新地址时…","publisher":{"name":"chinese-corpus","url":null},"homepage":"https://chinese-corpus.cn","repository":null,"version":"0.1.1","license":null,"protocols":["mcp"],"tags":["chinese-corpus","knowledge-service","mcp","model-context-protocol"],"pricing":null,"endpoints":[{"url":"pypi:chinese-corpus-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","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.756,"provenance":"derived"}],"categories":["dev"],"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":"chinese-corpus-mcp","registry":"pypi","observedAt":"2026-11-09T01:27:31.461Z","publishedAt":"2026-09-04T14:08:15.036979Z","latestVersion":"0.1.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"chinese-corpus-mcp","url":"https://pypi.org/project/chinese-corpus-mcp/","firstSeenAt":"2026-09-09T11:30:19.148Z","fetchedAt":"2026-11-09T01:26:38.356Z","normalizedAt":"2026-11-09T01:26:38.356Z"}]},"firstSeenAt":"2026-09-09T11:30:19.148Z","updatedAt":"2026-11-09T01:27:31.461Z"}