SpiderFoot MCP Server
A Model Context Protocol (MCP) server that provides SpiderFoot OSINT automation capabilities to AI assistants and other MCP clients.
Installation
pip install spiderfoot-mcp
Configuration
Set the following environment variables or create a .env file:
SPIDERFOOT_URL=http://localhost:5001
SPIDERFOOT_USERNAME=admin
SPIDERFOOT_PASSWORD=your_password
Usage
As MCP Server
Start the MCP server:
spiderfoot-mcp
The server will expose SpiderFoot functionality as MCP tools that can be used by AI assistants.
Available Tools
The MCP server provides the following tools:
start_scan: Start a new SpiderFoot scanget_scan_status: Get the current status of a scanlist_scans: List all scans on the serverstop_scan: Stop a running scandelete_scan: Delete a scan and its dataget_scan_results: Get results from a scanget_scan_summary: Get a summary of scan resultswait_for_scan_completion: Wait for a scan to completeexport_scan_results: Export scan results in various formatsget_available_modules: Get list of available SpiderFoot modulessearch_scan_results: Search across scan resultsget_scan_log: Get log entries for a scanget_active_scans_summary: Get summary of tracked scansping: Test connectivity to SpiderFoot server
MCP Client Configuration
To use this server with Claude Desktop or other MCP clients, add the following to your MCP configuration:
{
"mcpServers": {
"spiderfoot": {
"command": "spiderfoot-mcp",
"env": {
"SPIDERFOOT_URL": "http://localhost:5001",
"SPIDERFOOT_USERNAME": "admin",
"SPIDERFOOT_PASSWORD": "your_password"
}
}
}
}
Requirements
- Python 3.8+
- spiderfoot-client>=1.0.0
- fastmcp>=2.10.0
- python-dotenv>=1.0.0
- A running SpiderFoot instance
Dependencies
This package depends on the spiderfoot-client package, which provides the underlying SpiderFoot API client functionality.
License
MIT License