mcp-maigret
MCP server for maigret, a powerful OSINT tool that collects user account information from various public sources.
claude mcp add --transport stdio burtthecoder-mcp-maigret node /absolute/path/to/mcp-maigret/build/index.js \ --env MAIGRET_REPORTS_DIR="<path-to-reports-directory>"
How to use
Maigret MCP Server provides an interface to run the Maigret OSINT tool through MCP-compatible clients such as Claude Desktop. It exposes tools for searching usernames across hundreds of social networks and websites, and for analyzing URLs to extract associated information and usernames. The server is designed to be secure by validating inputs and passing commands as arguments, reducing the risk of shell injection. To use it, connect your MCP client to the configured server (named maigret in Claude Desktop configuration) and invoke the built-in tools like Username Search (search_username) and URL Analysis (parse_url) with the required parameters. Results can be produced in multiple formats (txt, html, pdf, json, csv, xmind) and can be filtered by site tags to tailor the scope of the search.
How to install
Prerequisites:
- Node.js v18 or later
- npm (comes with Node.js)
- Docker (optional, for Maigret container-based workflows)
- A Claude Desktop installation if you plan to connect via Claude
Option A: Install via Smithery (recommended for Claude Desktop integration)
- Ensure you have npm and npx installed with Node.js
- Install Maigret for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install mcp-maigret --client claude
Option B: Manual installation (from source)
- Install dependencies and build from source
git clone <repository_url>
cd mcp-maigret
npm install
npm run build
- Add to Claude Desktop configuration (example):
{
"mcpServers": {
"maigret": {
"command": "node",
"args": ["/absolute/path/to/mcp-maigret/build/index.js"],
"env": {
"MAIGRET_REPORTS_DIR": "/path/to/reports/directory"
}
}
}
}
- Start Claude Desktop and ensure the server appears in the available MCP servers.
Option C: Run via npm package globally
- Install globally
npm install -g mcp-maigret
- Run the server (adjust path as needed):
maigret --reports /path/to/reports
Notes:
- If you run from source, point Claude Desktop to the built index.js as shown above.
- The MAIGRET_REPORTS_DIR environment variable must be set to a writable directory where reports are saved.
Additional notes
- MAIGRET_REPORTS_DIR is required to store generated reports. Ensure the path exists and is writable by the user running the server.
- Input validation enforces that usernames contain only alphanumeric characters, underscores, hyphens, and periods, and that URLs are valid HTTP/HTTPS URLs without shell metacharacters.
- When running Docker-based workflows, ensure Docker is installed and the current user has permission to run Docker commands.
- If you encounter issues, check the server logs for validation errors or for failures in report generation, and verify that the configuration in Claude Desktop points to the correct command and environment variables.
- The server supports multiple output formats (txt, html, pdf, json, csv, xmind). Use the optional format parameter in the search tool to select the desired output.
Related MCP Servers
mcp-shodan
MCP server for querying the Shodan API
time
⏰ Time MCP Server: Giving LLMs Time Awareness Capabilities
unity-editor
An MCP server and client for LLMs to interact with Unity Projects
website-publisher
AI Website builder and publisher MCP. Quickly publish and deploy your AI generated code as real website URL. Support html, css, js, python etc.
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.
xgmem
Global Memory MCP server, that manage all projects data.