Sherlock MCP Server
Provides access to the Covertlabs infostealer intelligence platform to search for compromised credentials and investigate cyber threat artifacts. It enables security researchers to query databases for stolen emails, passwords, browser history, and victim metadata.
README
Sherlock MCP Server
An official Model Context Protocol (MCP) server for the Covertlabs infostealer intelligence platform. Built with FastMCP.
What is Sherlock?
Sherlock provides access to Covertlabs' comprehensive database of infostealer logs, enabling security researchers and threat intelligence teams to:
- Search compromised credentials by email, domain, username, or password
- Investigate victims by IP address, country, or stealer family
- Retrieve detailed artifacts including credentials, cookies, and browser history
Features
- 🔍 12 Search Tools - Comprehensive search capabilities across the infostealer database
- 🔐 Token Authentication - Secure access via Personal Access Tokens
- ⚡ Stateless HTTP - Scalable, load-balancer friendly architecture
- 🐳 Docker Ready - Production-ready containerization
Installation
Prerequisites
- Python 3.11+
- A Covertlabs account with API access
- Your Personal Access Token from app.covertlabs.io/cli/token
Quick Start
# Clone the repository
git clone https://github.com/covertlabs/sherlock-mcp.git
cd sherlock-mcp
# Create virtual environment
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
# Run the server
python server.py
Docker
docker compose up --build
Configuration
Configure via environment variables:
| Variable | Default | Description |
|---|---|---|
PORT |
8080 |
Server port |
HOST |
0.0.0.0 |
Server host |
COVERTLABS_API_URL |
https://api.covertlabs.io |
API endpoint |
CORS_ORIGINS |
* |
Allowed CORS origins |
LOG_REQUESTS |
false |
Enable request logging |
Client Configuration
Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"sherlock": {
"url": "http://localhost:8080/mcp",
"headers": {
"Authorization": "Bearer YOUR_TOKEN_HERE"
}
}
}
}
Claude Desktop
Add to your Claude Desktop MCP configuration:
{
"mcpServers": {
"sherlock": {
"url": "http://localhost:8080/mcp",
"headers": {
"Authorization": "Bearer YOUR_TOKEN_HERE"
}
}
}
}
Available Tools
See the docs/ folder for detailed documentation on each tool and response formats.
Search Tools
| Tool | Description |
|---|---|
search_by_email |
Search victims by email address |
search_by_domain |
Search victims by domain |
search_by_ip |
Search victims by IP address |
search_by_username |
Search victims by username |
search_by_password |
Search victims by password |
search_text |
Broad text search across all fields |
search_by_country |
Search by ISO country code |
search_by_stealer |
Search by stealer malware family |
Victim Detail Tools
| Tool | Description |
|---|---|
get_victim_profile |
Get victim profile and metadata |
get_victim_credentials |
Get stolen credentials |
get_victim_cookies |
Get stolen browser cookies |
get_victim_history |
Get browser history |
Authentication
This server uses Personal Access Token (PAT) authentication. Tokens are passed through to the Covertlabs API.
- Log in to app.covertlabs.io
- Navigate to CLI Token
- Copy your token (format:
cl_pat_V1_...) - Add to your MCP client configuration
API Endpoints
| Endpoint | Method | Description |
|---|---|---|
/ |
GET | Server information |
/health |
GET | Health check |
/mcp |
POST | MCP protocol endpoint |
Documentation
- Tools Reference - Detailed tool documentation
- Response Formats - API response schemas
- Examples - Usage examples
Support
- Documentation: docs.covertlabs.io
- Issues: GitHub Issues
- Email: support@covertlabs.io
License
MIT License - see LICENSE for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.