{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_quf4qgfe3vdd","handle":"company-mcp","url":"https://wellknown.network/agents/company-mcp","links":{"self":"https://wellknown.network/agents/company-mcp/record.json","html":"https://wellknown.network/agents/company-mcp","markdown":"https://wellknown.network/agents/company-mcp/record.md","api":"https://wellknown.network/api/v1/agents/company-mcp","status":"https://wellknown.network/api/v1/agents/company-mcp/status","claim":"https://wellknown.network/agents/company-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/company-mcp/claim.json","badge":"https://wellknown.network/agents/company-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/company-mcp/history","tools":"https://wellknown.network/api/v1/agents/company-mcp/tools"},"ard":{"identifier":"urn:air::server:company-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"company-mcp","summary":"MCP server for extracting AI companies and funding information from articles","description":"# Company MCP\n\n一个用于从文章中提取公司信息的 MCP (Model Context Protocol) 服务器，可识别 AI 领域公司及其融资信息。\n\n## 功能\n\n- 从给定的文章 URL 中提取所有公司名称\n- 判断每个公司是否为 AI 领域公司\n- 判断每个公司是否有融资信息\n- 使用 OpenRouter 对接 xiaomi/mimo-v2-flash 模型进行分析\n\n## 安装\n\n```bash\npip install company-mcp\n```\n\n或者从源码安装：\n\n```bash\ngit clone https://github.com/yourusername/company-mcp.git\ncd company-mcp\npip install -e .\n```\n\n## 配置\n\n创建 `.env` 文件或设置环境变量：\n\n```bash\nOPENROUTER_API_KEY=\"your-openrouter-api-key\"\nOPENROUTER_BASE_URL=\"https://openrouter.ai/api/v1\"\n```\n\n## 使用方式\n\n### 1. Stdio 模式（推荐用于 Claude Desktop）\n\n```bash\ncompany-mcp\n```\n\n在 Claude Desktop 的配置文件中添加：\n\n**macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`\n**Windows**: `%APPDATA%\\Claude\\claude_desktop_config.json`\n\n```json\n{\n  \"mcpServers\": {\n    \"company-mcp\": {\n      \"command\": \"company-mcp\",\n      \"env\": {\n        \"OPENROUTER_API_KEY\": \"your-api-key\"\n      }\n    }\n  }\n}\n```\n\n### 2. SSE 模式（HTTP 服务器）\n\n```bash\ncompany-mcp-sse\n```\n\n服务器将在 `http://localhost:8000` 启动。\n\n端点：\n- `GET /health` - 健康检查\n- `GET /sse` - SSE 连接端点\n- `POST /messages/` - 消息处理端点\n\n配置客户端连接到 SSE 端点：\n\n```json\n{\n  \"mcpServers\": {\n    \"company-mcp\": {\n      \"url\": \"http://localhost:8000/sse\"\n    }\n  }\n}\n```\n\n## 工具说明\n\n### extract_companies\n\n从文章 URL 中提取公司信息。\n\n**输入参数：**\n- `url` (string, 必需): 文章的 URL 地址\n\n**输出示例：**\n\n```json\n{\n  \"url\": \"https://example.com/article\",\n  \"companies\": [\n    {\n      \"company\": \"DeepWisdom（深度赋智）\",\n      \"reason\": \"是AI领域的，且官宣连续完成 A 轮及 A + 轮融资，累计金额达 3100 万美元\",\n      \"match\": true\n    },\n    {\n      \"company\": \"OpenAI\",\n      \"reason\": \"本文中没涉及到融资\",\n      \"match\": false\n    }\n  ],\n  \"total_count\": 2,\n  \"match_count\": 1\n}\n```\n\n## 发布到 PyPI\n\n1. 注册 PyPI 账号: https://pypi.org/account/register/\n\n2. 安装构建工具：\n```bash\npip install build twine\n```\n\n3. 构建包：\n```bash\npython -m build\n```\n\n4. 上传到 PyPI：\n```bash\ntwine upload dist/*\n```\n\n5. 上传到 TestPyPI（测试）：\n```bash\ntwine upload --repository testpypi dist/*\n```\n\n## 开发\n\n```bash\n# 安装依赖\nuv sync\n\n# 运行 stdio 服务器\nuv run company-mcp\n\n# 运行 SSE 服务器\nuv run company…","publisher":null,"homepage":"https://github.com/yourusername/company-mcp","repository":"https://github.com/yourusername/company-mcp","version":"0.1.0","license":null,"protocols":["mcp"],"tags":["ai","company","extraction","funding","mcp"],"pricing":null,"endpoints":[{"url":"pypi:company-mcp","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":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"},{"slug":"documents.extraction","name":"Data Extraction","confidence":1,"provenance":"declared"}],"categories":["dev","documents"],"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":"company-mcp","registry":"pypi","observedAt":"2026-10-27T22:27:47.415Z","publishedAt":"2026-01-31T11:41:14.128893Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"company-mcp","url":"https://pypi.org/project/company-mcp/","firstSeenAt":"2026-09-09T12:27:21.284Z","fetchedAt":"2026-10-27T22:26:38.316Z","normalizedAt":"2026-10-27T22:26:38.316Z"}]},"firstSeenAt":"2026-09-09T12:27:21.284Z","updatedAt":"2026-10-27T22:27:47.415Z"}