{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_7te83u68jwtp","handle":"iflow-mcp-vonequinox-websearchmcp","url":"https://wellknown.network/agents/iflow-mcp-vonequinox-websearchmcp","links":{"self":"https://wellknown.network/agents/iflow-mcp-vonequinox-websearchmcp/record.json","html":"https://wellknown.network/agents/iflow-mcp-vonequinox-websearchmcp","markdown":"https://wellknown.network/agents/iflow-mcp-vonequinox-websearchmcp/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-vonequinox-websearchmcp","status":"https://wellknown.network/api/v1/agents/iflow-mcp-vonequinox-websearchmcp/status","claim":"https://wellknown.network/agents/iflow-mcp-vonequinox-websearchmcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-vonequinox-websearchmcp/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-vonequinox-websearchmcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-vonequinox-websearchmcp/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-vonequinox-websearchmcp/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-vonequinox-websearchmcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_vonequinox-websearchmcp","summary":"MCP (Model Context Protocol) web search server (Brave search + fetch tools)","description":"#  WebSearch MCP Server\n\n一个基于 MCP (Model Context Protocol) 的智能网页搜索服务器，支持 AI 增强搜索、Brave 搜索和网页抓取功能。\n\n> **推荐**: 本项目推荐使用 `SOTASearch.py`，它结合了 AI 深度搜索和 Brave 搜索，**并行执行**两种搜索以提升速度。适合与 [CherryStudio](https://github.com/kangfenmao/cherry-studio) 配合使用。\n\n## 功能\n\n| 工具 | 说明 |\n|------|------|\n| `web_search` | AI 深度搜索 + Brave 搜索（并行执行），返回链接列表和 AI 总结 |\n| `fetch_html` | 抓取网页 HTML 内容 |\n| `fetch_text` | 抓取网页并提取纯文本 |\n| `fetch_metadata` | 抓取网页元数据（标题、描述、链接） |\n\n## 安装\n\n### 1. 克隆项目\n\n```bash\ngit clone https://github.com/yourusername/WebSearchMCP.git\ncd WebSearchMCP\n```\n\n### 2. 安装依赖\n\n**使用 uv（推荐）：**\n\n```bash\nuv sync\n```\n\n**使用 pip：**\n\n```bash\npip install -r requirements.txt\n```\n\n### 3. 配置环境变量\n\n复制 `.env.example` 为 `.env` 并填入配置：\n\n```bash\ncp .env.example .env\n```\n\n主要配置项：\n\n```env\n# 代理配置（可选）\nPROXY=http://127.0.0.1:7890\nCF_WORKER=https://your-worker.workers.dev\n\n# OpenAI API 配置（SOTASearch 必需）\nOPENAI_API_KEY=sk-xxx\nOPENAI_BASE_URL=https://api.openai.com/v1\nOPENAI_MODEL=gpt-4o\n```\n\n## 快速开始\n\n```bash\n# 使用 uv（推荐）\nuv run SOTASearch.py\n\n# 或使用 python\npython SOTASearch.py\n```\n\n## 配置 CherryStudio\n\n在 CherryStudio 的 MCP 服务器设置中添加（必须使用虚拟环境中的 Python 绝对路径）：\n\n**Windows 示例：**\n\n```json\n{\n  \"mcpServers\": {\n    \"sota-search\": {\n      \"name\": \"Websearch\",\n      \"type\": \"stdio\",\n      \"command\": \"D:\\\\Code\\\\github\\\\WebSearchMCP\\\\.venv\\\\Scripts\\\\python.exe\",\n      \"args\": [\"D:/Code/github/WebSearchMCP/SOTASearch.py\"]\n    }\n  }\n}\n```\n\n**macOS/Linux 示例：**\n\n```json\n{\n  \"mcpServers\": {\n    \"sota-search\": {\n      \"name\": \"Websearch\",\n      \"type\": \"stdio\",\n      \"command\": \"/path/to/WebSearchMCP/.venv/bin/python\",\n      \"args\": [\"/path/to/WebSearchMCP/SOTASearch.py\"]\n    }\n  }\n}\n```\n\n> **注意**: 推荐使用项目虚拟环境中的 Python 解释器（`.venv/Scripts/python.exe` 或 `.venv/bin/python`），确保依赖正确加载。系统 Python 也可以使用，但需确保已安装所有依赖。\n\n> **提示**: 代理和 API 配置建议写在 `.env` 文件中，无需在命令行参数中指定。\n\n## 命令行参数\n\n| 参数 | 说明 | 示例 |\n|------|------|------|\n| `--proxy` | 本地代理地址 | `--proxy http://127.0.0.1:7890` |\n| `--cf-worker` | Cloudflare Worker 地址 | `--cf-worker https://xxx.workers…","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_vonequinox-websearchmcp","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":"data.web-search","name":"Web Search","confidence":0.894,"provenance":"derived"},{"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":"iflow-mcp_vonequinox-websearchmcp","registry":"pypi","observedAt":"2026-09-15T20:21:35.683Z","publishedAt":"2026-02-06T18:02:41.262310Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_vonequinox-websearchmcp","url":"https://pypi.org/project/iflow-mcp_vonequinox-websearchmcp/","firstSeenAt":"2026-09-09T21:24:51.616Z","fetchedAt":"2026-09-15T20:20:34.623Z","normalizedAt":"2026-09-15T20:20:34.623Z"}]},"firstSeenAt":"2026-09-09T21:24:51.616Z","updatedAt":"2026-09-15T20:21:35.683Z"}