atomic-red-team-mcp

Provides an MCP (Model Context Protocol) server that exposes Atomic Red Team test content and operations, including searching for “atomics,” refreshing/downloading atomic definitions, validating atomic YAML, retrieving a validation schema, and (optionally) executing atomic tests when explicitly enabled.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Security mcp atomic-red-team security-testing validation execution-optional agent-tools
⚙ Agent Friendliness
60
/ 100
Can an agent use this?
🔒 Security
57
/ 100
Is it safe for agents?
⚡ Reliability
32
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
70
Documentation
75
Error Messages
0
Auth Simplicity
85
Rate Limits
10

🔒 Security

TLS Enforcement
80
Auth Strength
55
Scope Granularity
20
Dep. Hygiene
60
Secret Handling
70

Execution is explicitly disabled by default (ART_EXECUTION_ENABLED=false) with a warning about dangerous security tests. Optional static bearer token authentication (ART_AUTH_TOKEN) can protect remote hosting, but it is static and appears coarse-grained (no scoped permissions). TLS transport enforcement is not explicitly stated in the provided text; transport is configurable (ART_MCP_TRANSPORT). Secrets guidance recommends not committing tokens, implying expected safe handling.

⚡ Reliability

Uptime/SLA
0
Version Stability
55
Breaking Changes
40
Error Recovery
35
AF Security Reliability

Best When

Used locally or in a locked-down test environment where tool execution is disabled by default or tightly controlled.

Avoid When

Avoid enabling execute capability on systems where untrusted users or agents can trigger test execution.

Use Cases

  • Integrate Atomic Red Team test discovery into AI assistants via MCP tools
  • Validate Atomic Red Team atomic test YAML before publishing/using
  • Programmatically search and enumerate atomic tests by technique ID, name, description, or platform
  • Optionally execute selected atomic tests in controlled environments

Not For

  • Internet-facing production use without strong authentication and isolation
  • Running destructive or state-changing tests in uncontrolled environments
  • Use as a general-purpose orchestration tool without guardrails for execution

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Static bearer token (ART_AUTH_TOKEN) via Authorization: Bearer <token>
OAuth: No Scopes: No

Authentication is disabled by default unless ART_AUTH_TOKEN is set. Token is static (no OAuth flow) and appears to gate all MCP tool/resource access when enabled.

Pricing

Free tier: No
Requires CC: No

README mentions an optional remote server (hosted on Railway) with a free tier, but no concrete limits or pricing are provided in the provided content.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • execute_atomic is disabled by default; enabling ART_EXECUTION_ENABLED can cause potentially dangerous system changes
  • If auth is not configured (ART_AUTH_TOKEN unset), an MCP server may be accessible without authentication when exposed remotely

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for atomic-red-team-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered