{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_ng8zrdhuwek2","handle":"mcp-bocha-search","url":"https://wellknown.network/agents/mcp-bocha-search","links":{"self":"https://wellknown.network/agents/mcp-bocha-search/record.json","html":"https://wellknown.network/agents/mcp-bocha-search","markdown":"https://wellknown.network/agents/mcp-bocha-search/record.md","api":"https://wellknown.network/api/v1/agents/mcp-bocha-search","status":"https://wellknown.network/api/v1/agents/mcp-bocha-search/status","claim":"https://wellknown.network/agents/mcp-bocha-search/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-bocha-search/claim.json","badge":"https://wellknown.network/agents/mcp-bocha-search/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-bocha-search/history","tools":"https://wellknown.network/api/v1/agents/mcp-bocha-search/tools"},"ard":{"identifier":"urn:air::server:mcp-bocha-search","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-bocha-search","summary":"博查是一个给AI用的搜索引擎，让你的AI应用从近百亿网页和生态内容源中获取高质量的世界知识","description":"# MCP Server 产品名称: 博查\n\n![Bocha Search MCP Server](assets/bocha-logo-720x180.png)\n\n## 产品描述\n### 短描述\n博查是一个给AI用的搜索引擎，让你的AI应用从近百亿网页和生态内容源中获取高质量的世界知识，涵盖天气、新闻、百科、医疗、火车票、图片等多种领域。\n\n### 长描述\n博查是一个给AI用的搜索引擎，让你的AI应用从近百亿网页和生态内容源中获取高质量的世界知识，涵盖天气、新闻、百科、医疗、火车票、图片等多种领域。\n\n## 分类\n网页搜索\n\n## 标签\n搜索, 新闻, 天气, 百科\n\n## Tools\n### Tool1: Bocha Web Search\n#### 详细描述\n从博查搜索全网信息和网页链接，返回结果包括网页标题、网页URL、网页摘要、网站名称、网站图标、发布时间、图片链接等。\n\n#### 调试所需要的参数\n输入:\n  - query: 搜索词(必填)\n  - freshness: 搜索指定时间范围内的网页 (可选值 YYYY-MM-DD, YYYY-MM-DD..YYYY-MM-DD, noLimit, oneYear, oneMonth, oneWeek, oneDay. 默认为 noLimit)\n  - count: 返回结果的条数 (1-50, 默认为 10)\n\n输出:\n  - 网页标题、网页链接、网页摘要、发布时间、网站名称\n\n### Tool2: Bocha AI Search\n#### 详细描述\n在博查网页搜索的基础上，AI识别搜索词语义并额外返回垂直领域内容的结构化模态卡，例如天气卡、日历卡、百科卡等几十种模态卡，在语义识别、搜索结果时效性、内容丰富性等方面更好。\n\n#### 调试所需要的参数\n输入:\n  - query: 搜索词(str, 必填)\n  - freshness: 搜索指定时间范围内的网页 (可选值 YYYY-MM-DD, YYYY-MM-DD..YYYY-MM-DD, noLimit, oneYear, oneMonth, oneWeek, oneDay. 默认为 noLimit)\n  - count: 返回结果的条数 (1-50, 默认为 10)\n\n输出:\n  - 网页标题、网页链接、网页摘要、发布时间、网站名称、模态卡\n\n## 可适配平台\n方舟, python, Claude, Cursor等\n\n## 服务开通链接\n您需要前往 [博查AI开放平台](https://open.bochaai.com)，登陆后获取 API KEY。\n\n## 鉴权方式\nAPI Key\n\n## 安装部署\n### 步骤一：下载代码至本地\n```bash\ngit clone git@github.com:shibing624/mcp-bocha-search.git\n```\n\n### 步骤二: 在客户端中配置\n#### Claude Desktop\nOn MacOS: `~/Library/Application\\ Support/Claude/claude_desktop_config.json`\n\nOn Windows: `%APPDATA%/Claude/claude_desktop_config.json`\n\n```json\n  \"mcpServers\": {\n    \"mcp-bocha-search\": {\n      \"command\": \"uvx\",\n      \"args\": [ \"mcp-bocha-search\" ],\n      \"env\": {\n        \"BOCHA_API_KEY\": \"sk-****\"\n      }\n    }\n  }\n  ```\n\n### 步骤三: 在客户端中使用\n![示例: alibaba 2024 esg report](assets/alibaba-2024-esg-report.png)\n\n### 步骤四: 调试本地服务（可选）\n```bash\nnpx @modelcontextprotocol/inspector uv run mcp-bocha-search\n```\n\n## 客户案例\n\n目前博查已经累计服务**3000+企业用户**和**20000+开发者用户**，并且成为**DeepSeek官方联网搜索供应方**以及**阿里、腾讯、字节官方推荐的搜索API**，目前**承接着国内60%以上AI应用的联网搜索请求**。\n\n博查的搜索内容源包括全网近百亿个网页，以及生态合作内容（含短视频、新闻、百科、天气、医疗、火车票、酒店、餐厅、景点、企业、学术等）。博查后续将会继续与各个平台在内容生态、智能体创作等方面开展共创合作，为博查用户的搜索问题提供丰富多彩…","publisher":null,"homepage":"https://open.bochaai.com","repository":"https://github.com/shibing624/mcp-bocha-search","version":"0.0.1","license":null,"protocols":["mcp"],"tags":["ai-search","bocha","mcp","search","web-search"],"pricing":null,"endpoints":[{"url":"pypi:mcp-bocha-search","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"data.web-search","name":"Web Search","confidence":1,"provenance":"declared"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["data","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":"mcp-bocha-search","registry":"pypi","observedAt":"2026-10-28T10:24:19.340Z","publishedAt":"2025-12-13T13:47:03.214849Z","latestVersion":"0.0.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-bocha-search","url":"https://pypi.org/project/mcp-bocha-search/","firstSeenAt":"2026-09-10T00:24:31.305Z","fetchedAt":"2026-10-28T10:22:44.562Z","normalizedAt":"2026-10-28T10:22:44.562Z"}]},"firstSeenAt":"2026-09-10T00:24:31.305Z","updatedAt":"2026-10-28T10:24:19.340Z"}