mcp-bitsight

mcp-bitsight

Exposes BitSight Security Ratings as tools for AI assistants, enabling queries on company security scores, company search, details, vulnerabilities, portfolio, risk vectors, and alerts.

Category
访问服务器

README

mcp-bitsight

A focused Model Context Protocol (MCP) server that exposes BitSight Security Ratings as tools for AI assistants.

Note: This repo will be renamed from mcp-gateway to mcp-bitsight to reflect its single purpose.

Architecture Context

This is one component in a larger MCP architecture:

┌─────────────┐     ┌──────────────┐     ┌──────────────┐     ┌──────────────┐
│    User     │────▶│  LLM Layer   │────▶│  MCP Gateway │────▶│ mcp-bitsight │ ← This repo
│  (Cursor)   │     │ (AI Foundry) │     │   (Router)   │     │              │
└─────────────┘     └──────────────┘     └──────┬───────┘     └──────────────┘
                                                │
                                                ├────▶ mcp-servicenow (future)
                                                └────▶ mcp-* (future)
Component Purpose Repo
mcp-bitsight BitSight API tools This repo
mcp-gateway Routes to MCP servers Separate repo (TBD)
ai-orchestrator LLM reasoning layer Separate repo (TBD)

Available Tools

Tool Description
get_bitsight_score Get security rating for any company by name
search_companies Search for companies in BitSight
get_company_details Get full company details by GUID
get_security_findings Get vulnerabilities and security findings
get_portfolio View your monitored companies
get_risk_vectors List all risk categories
get_alerts Get portfolio alerts

Quick Start

1. Clone and Setup

git clone https://github.com/your-org/mcp-bitsight.git
cd mcp-bitsight

# Create virtual environment
python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -e .

2. Configure Environment

Create a .env file:

BITSIGHT_API_TOKEN=your-api-key-here
LOG_LEVEL=WARNING

3. Connect to Cursor

Add to ~/.cursor/mcp.json (macOS/Linux) or %USERPROFILE%\.cursor\mcp.json (Windows):

{
  "mcpServers": {
    "bitsight": {
      "command": "/full/path/to/mcp-bitsight/venv/bin/python",
      "args": ["/full/path/to/mcp-bitsight/main.py"],
      "cwd": "/full/path/to/mcp-bitsight"
    }
  }
}

4. Restart Cursor

After updating mcp.json, restart Cursor completely (Cmd+Q / Alt+F4, then reopen).

Corporate Proxy / SSL Certificates

If behind a corporate firewall that intercepts HTTPS, place CA certificates in certs/:

certs/
├── combined_ca_bundle.pem
└── ca_bundle.pem

Or set via environment:

MCP_CA_BUNDLE=/path/to/your/ca_bundle.pem

Cloud Deployment (Azure)

CI/CD

Push to dev branch triggers automatic build and deploy via GitHub Actions.

Required GitHub Secrets:

Secret Description
ACR_LOGIN_SERVER ACR login server
ACR_USERNAME Azure Container Registry username
ACR_PASSWORD Azure Container Registry password
AZURE_CLIENT_ID Service principal client ID
AZURE_TENANT_ID Azure AD tenant ID
AZURE_SUBSCRIPTION_ID Azure subscription ID

Connect Cursor to Cloud

{
  "mcpServers": {
    "bitsight": {
      "url": "https://your-app.azurecontainerapps.io/sse"
    }
  }
}

Project Structure

mcp-bitsight/
├── app/
│   ├── __init__.py
│   ├── bitsight.py      # BitSight API client
│   └── server.py        # MCP tools
├── certs/               # SSL certificates
├── Documentation/
├── .github/workflows/   # CI/CD
├── main.py              # Entry point
├── pyproject.toml       # Dependencies
└── Dockerfile

Environment Variables

Variable Description Default
BITSIGHT_API_TOKEN BitSight API key Required
MCP_TRANSPORT stdio or http stdio
PORT HTTP port 8000
LOG_LEVEL DEBUG, INFO, WARNING, ERROR WARNING
MCP_CA_BUNDLE Custom CA certificate path Auto-detected

Development

pip install -e ".[dev]"
pytest
ruff check .
ruff format .

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选