Company MCP
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。
功能
- 从给定的文章 URL 中提取所有公司名称
- 判断每个公司是否为 AI 领域公司
- 判断每个公司是否有融资信息
- 使用 OpenRouter 对接 xiaomi/mimo-v2-flash 模型进行分析
安装
pip install company-mcp
或者从源码安装:
git clone https://github.com/yourusername/company-mcp.git
cd company-mcp
pip install -e .
配置
创建 .env 文件或设置环境变量:
OPENROUTER_API_KEY="your-openrouter-api-key"
OPENROUTER_BASE_URL="https://openrouter.ai/api/v1"
使用方式
1. Stdio 模式(推荐用于 Claude Desktop)
company-mcp
在 Claude Desktop 的配置文件中添加:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"company-mcp": {
"command": "company-mcp",
"env": {
"OPENROUTER_API_KEY": "your-api-key"
}
}
}
}
2. SSE 模式(HTTP 服务器)
company-mcp-sse
服务器将在 http://localhost:8000 启动。
端点:
GET /health- 健康检查GET /sse- SSE 连接端点POST /messages/- 消息处理端点
配置客户端连接到 SSE 端点:
{
"mcpServers": {
"company-mcp": {
"url": "http://localhost:8000/sse"
}
}
}
工具说明
extract_companies
从文章 URL 中提取公司信息。
输入参数:
url(string, 必需): 文章的 URL 地址
输出示例:
{
"url": "https://example.com/article",
"companies": [
{
"company": "DeepWisdom(深度赋智)",
"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",
"match": true
},
{
"company": "OpenAI",
"reason": "本文中没涉及到融资",
"match": false
}
],
"total_count": 2,
"match_count": 1
}
发布到 PyPI
-
注册 PyPI 账号: https://pypi.org/account/register/
-
安装构建工具:
pip install build twine
- 构建包:
python -m build
- 上传到 PyPI:
twine upload dist/*
- 上传到 TestPyPI(测试):
twine upload --repository testpypi dist/*
开发
# 安装依赖
uv sync
# 运行 stdio 服务器
uv run company-mcp
# 运行 SSE 服务器
uv run company-mcp-sse
# 使用 MCP Inspector 测试
npx @modelcontextprotocol/inspector company-mcp
License
MIT
Metadata
Release files for company-mcp 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| company_mcp-0.1.0.tar.gz | 46.5 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| company_mcp-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 55.9 kB
Release files / company_mcp-0.1.0.tar.gz
| Download URL | company_mcp-0.1.0.tar.gz |
|---|---|
| Size | 46.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5fd2dbdb676986ede3879ba8141853b3f5b1cc185be452a3b35107abade7e9d8
|
|
BLAKE2b-256 checksum How to use checksums |
0b9c3c068fd19355643f58bb312a733e8d4e84c8ada36ece47fcfdcb3db7fc99
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.12
|
Release files / company_mcp-0.1.0-py3-none-any.whl
| Download URL | company_mcp-0.1.0-py3-none-any.whl |
|---|---|
| Size | 9.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a3d968110210ccdcc7a7ff96f9bc7d52ee18249abedc0a131e508a0f3968005b
|
|
BLAKE2b-256 checksum How to use checksums |
036c5ce861d8e5a0af31d5b465d9a595f6b0324c40faeba7442e07c9e7b1b690
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.12
|
Security for company-mcp 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.