MITRE ATLAS MCP
Exposes the MITRE ATLAS adversarial AI threat landscape over the Model Context Protocol, providing tactics and techniques for attacking AI systems. It supports EU AI Act compliance features including risk management, transparency, bias detection, and AI content watermarking.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Query adversarial AI threat landscape
- Check EU AI Act compliance articles
- Detect bias in AI models
- Support FRIA documentation
Source and maintenance
- Last repository push
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
mitre-atlas-mcp 1.0.9
{
"version": "1.0.9",
"transport": "stdio",
"identifier": "mitre-atlas-mcp",
"runtimeHint": "python",
"registryType": "pypi"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · repository · passed · metadata changed · updated
- · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown
Let your agent find its tools
Find servers like MITRE ATLAS MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.