Skip to main content

MCP server for ATT&CK queries via AI assistants

Project description

attack-query-mcp

MCP server for ATT&CK queries via AI assistants.

Overview

This package provides a Model Context Protocol (MCP) server that enables AI assistants like Claude to query MITRE ATT&CK data using natural language.

Installation

pip install attack-query-mcp

Usage

With Claude Desktop

Add to your Claude Desktop configuration (claude_desktop_config.json):

{
  "mcpServers": {
    "attack-query": {
      "command": "attack-query-mcp"
    }
  }
}

Standalone

attack-query-mcp

Tools

The MCP server provides 7 tools for querying ATT&CK data:

Tool Description
query_attack Natural language queries (e.g., "techniques used by APT28")
get_technique Get technique details by ID (e.g., T1566)
get_group Get group info by name, ID, or alias
compare_groups Compare techniques between two groups with similarity metrics
find_similar_groups Find groups with similar technique profiles
get_mitigations Get mitigations for a technique
export_navigator_layer Export techniques as Navigator layer JSON

Example Tool Usage

User: What techniques does APT28 use for initial access?
AI: [calls query_attack with "techniques used by APT28 for initial access"]

User: Compare APT28 and APT29
AI: [calls compare_groups with group1="APT28", group2="APT29"]

User: What mitigations address phishing?
AI: [calls get_mitigations with technique_id="T1566"]

Resources

The MCP server exposes 6 resources for browsing ATT&CK data:

URI Description
attack://groups List all threat groups with IDs, names, and aliases
attack://techniques List all techniques with IDs, names, and tactics
attack://tactics List all tactics in kill chain order
attack://software List all software (malware and tools)
attack://mitigations List all mitigations with technique counts
attack://campaigns List all campaigns with dates and attribution

Example Resource Usage

User: Show me all APT groups in ATT&CK
AI: [reads attack://groups resource]

User: What tactics are in the kill chain?
AI: [reads attack://tactics resource]

Requirements

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

attack_query_mcp-0.2.0.tar.gz (15.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

attack_query_mcp-0.2.0-py3-none-any.whl (11.6 kB view details)

Uploaded Python 3

File details

Details for the file attack_query_mcp-0.2.0.tar.gz.

File metadata

  • Download URL: attack_query_mcp-0.2.0.tar.gz
  • Upload date:
  • Size: 15.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.11 {"installer":{"name":"uv","version":"0.9.11"},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for attack_query_mcp-0.2.0.tar.gz
Algorithm Hash digest
SHA256 19569c06ef4ab6a7fcb20adf229be981ceaf4119881c95621b12c2273eb618d0
MD5 3df0e0044cf490fb4536f01c39505f79
BLAKE2b-256 a99e72890c7e6e7214a246ce8c8da1801be9032bae70a90e648f4a89afd33d27

See more details on using hashes here.

File details

Details for the file attack_query_mcp-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: attack_query_mcp-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 11.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.11 {"installer":{"name":"uv","version":"0.9.11"},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for attack_query_mcp-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 4ee549046dd0092fdbeef6027f5f3f35be4616f72c16684f9dd63e68f2efe495
MD5 eb38247a1b088e1f24be69af2b3bf9bd
BLAKE2b-256 8c2065ec3b092ac29b6610fba2aee894e0e49e0602eabb4663cbac68419c3b8e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page