About VirusTotal
VirusTotal is a security-analysis MCP server built with FastMCP and Python for investigating URLs, files, IP addresses, and domains from AI assistants. It automatically fetches related threat data and supports paginated follow-up queries.
Key features
- 01Analyze URLs, files, IPs, and domains
- 02Automatically fetch related threat data
- 03Query DNS, WHOIS, and SSL information
- 04Paginate queries for specific relationships
- 05Support SSE and STDIO transports
- 06Respect VirusTotal API rate limits
Use cases
- 01Review a suspicious URL and its related entities
- 02Investigate file behavior and network connections by hash
- 03Check IP or domain reputation and historical relationships
- 04Explore specific relationship data with pagination
MCP support
The server provides MCP clients with report and relationship-query tools for URLs, files, IPs, and domains. It supports SSE and STDIO transports.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEVirusTotal MCP Server
A Model Context Protocol (MCP) server for comprehensive security analysis using the VirusTotal API. Built with FastMCP and Python, this server provides AI assistants like Claude with powerful malware detection and threat intelligence capabilities.
Overview
This MCP server integrates VirusTotal's extensive security database, allowing AI assistants to perform comprehensive security analysis on URLs, files, IP addresses, and domains. The server automatically fetches relationship data to provide complete security context in a single request.
Features
- Comprehensive Security Analysis: Complete threat analysis with automatic relationship fetching
- URL Analysis: Security reports with contacted domains, downloaded files, and threat actors
- File Analysis: Detailed file hash analysis including behaviors, dropped files, and network connections
- IP Analysis: Geolocation, reputation data, and historical information
- Domain Analysis: DNS records, WHOIS data, SSL certificates, and subdomains
- Detailed Relationship Queries: Paginated access to specific relationship types for deep investigation
- Rate Limit Aware: Respects VirusTotal API limitations
- Multiple Transport Support: SSE and STDIO transports for different integration needs
Quick Start
Prerequisites
- Python 3.8+ or Docker
- uv package manager (for local development)
- VirusTotal API key (Get one here)
Installation
Option 1: Docker (Recommended)
-
Clone and setup:
git clone https://github.com/barvhaim/virustotal-mcp-server.git cd virustotal-mcp-server -
Configure API key:
echo "VIRUSTOTAL_API_KEY=your_api_key_here" > .env -
Run with Docker Compose:
docker-compose up -d -
Or run with Docker directly:
docker build -t virustotal-mcp . docker run -d --name virustotal-mcp -p 8000:8000 --env-file .env virustotal-mcp
Option 2: Local Development
-
Clone and setup:
git clone https://github.com/barvhaim/virustotal-mcp-server.git cd virustotal-mcp-server uv sync -
Configure API key:
echo "VIRUSTOTAL_API_KEY=your_api_key_here" > .env -
Run the server:
# SSE transport (web-friendly) uv run main.py # STDIO transport (for Claude Desktop) MCP_TRANSPORT=stdio uv run main.py
Tools Available
Report Tools (with Automatic Relationship Fetching)
1. URL Report Tool
- Name:
get_url_report - Description: Get comprehensive URL analysis including security scan results and key relationships
- Parameters:
url(required): The URL to analyze
- Auto-fetched relationships: communicating files, contacted domains/IPs, downloaded files, redirects, threat actors
2. File Report Tool
- Name:
get_file_report - Description: Get comprehensive file analysis using hash (MD5/SHA-1/SHA-256)
- Parameters:
hash(required): File hash to analyze
- Auto-fetched relationships: behaviors, dropped files, contacted domains/IPs, embedded URLs, threat actors
3. IP Report Tool
- Name:
get_ip_report - Description: Get comprehensive IP address analysis including geolocation and reputation
- Parameters:
ip(required): IP address to analyze
- Auto-fetched relationships: communicating files, historical SSL certificates, resolutions, threat actors
4. Domain Report Tool
- Name:
get_domain_report - Description: Get comprehensive domain analysis including DNS and WHOIS data
- Parameters:
domain(required): Domain name to analyzerelationships(optional): Specific relationships to include
- Auto-fetched relationships: subdomains, historical SSL certificates, resolutions, threat actors
Relationship Tools (for Detailed Analysis)
1. URL Relationship Tool
- Name:
get_url_relationship - Description: Query specific relationship types for URLs with pagination
- Parameters:
url(required): The URL to analyzerelationship(required): Relationship type (analyses, communicating_files, contacted_domains, etc.)limit(optional, 1-40, default: 10): Number of resultscursor(optional): Pagination cursor
2. File Relationship Tool
- Name:
get_file_relationship - Description: Query specific relationship types for files with pagination
- Parameters:
hash(required): File hashrelationship(required): Relationship type (behaviours, dropped_files, contacted_domains, etc.)limit(optional, 1-40, default: 10): Number of resultscursor(optional): Pagination cursor
3. IP Relationship Tool
- Name:
get_ip_relationship - Description: Query specific relationship types for IPs with pagination
- Parameters:
ip(required): IP addressrelationship(required): Relationship type (communicating_files, resolutions, etc.)limit(optional, 1-40, default: 10): Number of resultscursor(optional): Pagination cursor
4. Domain Relationship Tool
- Name:
get_domain_relationship - Description: Query specific relationship types for domains with pagination
- Parameters:
domain(required): Domain namerelationship(required): Relationship type (subdomains, historical_ssl_certificates, etc.)limit(optional, 1-40, default: 10): Number of resultscursor(optional): Pagination cursor
Claude Desktop Integration
To connect this server to Claude Desktop, add the following to your claude_desktop_config.json:
Configuration file locations:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Linux:
~/.config/claude/claude_desktop_config.json - Windows:
%APPDATA%\\Claude\\claude_desktop_config.json
{
"mcpServers": {
"virustotal": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/virustotal-mcp-server",
"run",
"main.py"
],
"env": {
"VIRUSTOTAL_API_KEY": "your_api_key_here",
"MCP_TRANSPORT": "stdio"
}
}
}
}
Resources
- FastMCP Documentation: github.com/jlowin/fastmcp
- MCP Specification: modelcontextprotocol.io
- VirusTotal API: developers.virustotal.com
- uv Package Manager: astral.sh/uv
- Claude Desktop: claude.ai
Version History
- v1.0.0: Initial release with comprehensive VirusTotal integration
- 8 security analysis tools
- Automatic relationship fetching
- SSE and STDIO transport support
- Rate limiting awareness
- Complete error handling
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.