About Exposureguard Mcp
This MCP server connects AI assistants to the ExposureGuard domain security scanning API. It supports domain checks, cached grade lookups, and remediation guidance, with results including A–F grades and fix snippets.
Key features
- 01Run a full scan with eight checks
- 02Retrieve cached grades
- 03Return A–F grades, scores, and report URLs
- 04Provide snippets for failed checks
- 05List third-party scripts and resources loaded by a domain
Use cases
- 01Check a domain's security configuration
- 02Quickly retrieve a recent security grade
- 03Find fixes for security issues
- 04Inventory third-party resources loaded by a domain
MCP support
The MCP server exposes ExposureGuard tools for domain scans, grade lookups, remediation guidance, and third-party resource queries.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEExposureGuard MCP Server
An MCP (Model Context Protocol) server that connects AI assistants to the ExposureGuard domain security scanning API.
Tools
| Tool | Description |
|---|---|
scan_domain | Full security scan — 8 checks, A-F grade, score, findings, report URL (~8s) |
get_grade | Cached grade lookup (up to 24h old) — fast, no new scan triggered |
get_remediation | Copy-paste fix snippets for all failing checks |
get_dependencies | Third-party scripts/resources loaded by the domain |
Setup
1. Get an API Key
Sign up at getexposureguard.com and grab your API key from the dashboard.
2. Install
# Option A: pip install (recommended)
pip install -e /path/to/exposureguard-mcp
# Option B: just install deps
pip install mcp httpx
3. Configure Your AI Client
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"exposureguard": {
"command": "python",
"args": ["-m", "exposureguard_mcp.server"],
"env": {
"EXPOSUREGUARD_API_KEY": "your-api-key-here"
}
}
}
}
If you installed as a package, you can also use:
{
"mcpServers": {
"exposureguard": {
"command": "exposureguard-mcp",
"env": {
"EXPOSUREGUARD_API_KEY": "your-api-key-here"
}
}
}
}
Cursor
Edit .cursor/mcp.json in your project root (or globally at ~/.cursor/mcp.json):
{
"mcpServers": {
"exposureguard": {
"command": "python",
"args": ["-m", "exposureguard_mcp.server"],
"env": {
"EXPOSUREGUARD_API_KEY": "your-api-key-here"
}
}
}
}
Windsurf
Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"exposureguard": {
"command": "python",
"args": ["-m", "exposureguard_mcp.server"],
"env": {
"EXPOSUREGUARD_API_KEY": "your-api-key-here"
}
}
}
}
VS Code (Copilot)
Edit .vscode/mcp.json in your project:
{
"servers": {
"exposureguard": {
"type": "stdio",
"command": "python",
"args": ["-m", "exposureguard_mcp.server"],
"env": {
"EXPOSUREGUARD_API_KEY": "your-api-key-here"
}
}
}
}
4. Usage Examples
Once connected, ask your AI assistant:
- "Scan example.com for security issues"
- "What's the security grade for cloudflare.com?"
- "Show me how to fix the security issues on my-site.com"
- "What third-party scripts does shopify.com load?"
Running Standalone
export EXPOSUREGUARD_API_KEY=your-api-key-here
python -m exposureguard_mcp.server
The server communicates over stdio using the MCP protocol — it's designed to be launched by an MCP client, not used interactively.
Rate Limits
Rate limits depend on your ExposureGuard plan. If you hit a 429 response, the server will return a message suggesting you upgrade at getexposureguard.com/pricing.
Publishing
PyPI
pip install build twine
python -m build
twine upload dist/*
Then users install with: pip install exposureguard-mcp
npm
npm publish
Then users install with: npx exposureguard-mcp
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.