sherlock

Sherlock MCP Server: Find truth and counter propaganda through ethical OSINT. FastMCP integration for social media username searches across 400+ platforms using Model Context Protocol. Empowering investigators, journalists, and AI assistants with transparent, verifiable tools.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio burnsedia-sherlock-mcp python main.py \
  --env SHERLOCK_TIMEOUT="timeout in seconds (optional)" \
  --env SHERLOCK_DEPLOYMENT="Set to 'local' or appropriate deployment mode if required"

How to use

Sherlock MCP Server exposes the Sherlock OSINT tool via the Model Context Protocol. It uses the Sherlock CLI under the hood to search for social media accounts associated with a given username and returns a structured list of found profiles, including site, URL, and existence status. This MCP server is implemented in Python and is designed to be run alongside other MCP-enabled AI assistants or clients that communicate over stdio. Once started, you can send MCP commands to perform a username search, and you will receive a JSON-formatted response with the results and a total count.

How to install

Prerequisites:

Python 3.13+ installed on your system
Git installed
Optional: Sherlock CLI tool (installed via pipx) for local verification

Installation steps:

Clone the repository:

git clone <repo-url>
cd sherlock-mcp

Install the MCP server package in editable mode:

pip install -e .

Ensure Sherlock is installed (optional for local verification):

pipx install sherlock-project

Run the server:

python main.py

Connect MCP clients via stdio pipes or configure an appropriate transport as needed.

Note: The README indicates Python 3.13+ compatibility and uses the Sherlock CLI for username searches.

Additional notes

Tips and notes:

The MCP server name is sherlock and is implemented in Python. Start the server with python main.py and connect MCP clients via stdio or suitable transport.
If you plan to run in a container, you can adapt the Python command to execute inside the container or use a dedicated Dockerfile (not provided in this snippet).
Environment variables shown in the config include SHERLOCK_DEPLOYMENT and SHERLOCK_TIMEOUT as placeholders. You can adjust or add env vars as needed by your deployment environment.
If Sherlock is not found or not installed, install with pipx install sherlock-project as noted in the prerequisites to ensure the underlying tool is available for the MCP server to query.
For best results, ensure network access to the platforms Sherlock queries and monitor rate limits to avoid blocks or timeouts.

Related MCP Servers

lc2mcp

Convert LangChain tools to FastMCP tools

MCPHammer

MCP security testing framework for evaluating Model Context Protocol server vulnerabilities

skill-to

Convert AI Skills (Claude Skills format) to MCP server resources - Part of BioContextAI

shodan

Shodan MCP server for Claude, Cursor & VS Code. 20 tools for passive reconnaissance, CVE/CPE intelligence, DNS analysis, and device search. 4 tools work free without an API key. OSINT and vulnerability research from your IDE.

fastmcp-builder

A comprehensive Claude Code skill for building production-ready MCP servers using FastMCP. Includes reference guides, runnable examples, and a complete implementation with OAuth, testing, and best practices.

openroad

Model Context Protocol (MCP) server for OpenROAD