Skip to main content
Glama
@mhdd_24/ai-red-team-mcp

@mhdd_24/ai-red-team-mcp

by Mhdd-24

@mhdd_24/ai-red-team-mcp

MCP server for Structured robustness/security testing.

Same architecture as @mhdd_24/sublime-mcp.

Full documentation: docs/WIKI.md


How it works (30 seconds)

You (chat) → MCP client → ai-red-team-mcp → AI Red Team APIs / CLIs / local tools

Related MCP server: EVIDIQ Bulwark

Prerequisites

Requirement

Notes

Node.js 18+

ESM TypeScript MCP server

Credentials / CLIs

See environment variables below


Install

Option A — npm (after publish)

npm install -g @mhdd_24/ai-red-team-mcp

Option B — npx

npx @mhdd_24/ai-red-team-mcp

Option C — clone and build

git clone https://github.com/Mhdd-24/AI-Red-Team-MCP.git
cd AI-Red-Team-MCP
npm install
npm run build
node dist/index.js

Configure Cursor

Edit ~/.cursor/mcp.json:

{
  "mcpServers": {
    "airedteam": {
      "command": "npx",
      "args": ["-y", "@mhdd_24/ai-red-team-mcp"],
      "env": {
        "_": "optional"
      }
    }
  }
}

Local development:

{
  "command": "node",
  "args": ["/absolute/path/to/AI-Red-Team-MCP/dist/index.js"]
}

Environment variables

Variable

Description

—

No required env


Tools

Tool

Description

airedteam_status

Show Structured robustness/security testing configuration / health.

airedteam_scan

Scan text for policy/safety issues.

airedteam_suite

Generate a test suite outline.


License

ISC

Available Tools

3 tools
airedteam_scanC

Scan text for policy/safety issues.

Inputs: text (required).

airedteam_statusB

Show Structured robustness/security testing configuration / health.

Inputs: no named parameters.

airedteam_suiteC

Generate a test suite outline.

Inputs: policy (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clear, distinct purpose: status shows health/configuration, scan performs direct text analysis, and suite generates a test plan. There is no realistic confusion between them.

    Naming Consistency4/5

    All tools share the consistent airedteam_ prefix and use lowercase snake_case, making the naming predictable. However, they do not follow a strict verb_noun pattern: scan is a verb while status and suite are nouns.

    Tool Count5/5

    Three tools is at the lower end of the well-scoped range, but each one earns its place in a focused red-team utility server. There is no redundancy or unnecessary bloat.

    Completeness3/5

    The set covers health/status, text scanning, and test-suite outline generation, but there is no tool to execute a generated suite or retrieve detailed scan results. This leaves notable gaps in a full red-team testing workflow.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables scanning LLM prompts and responses for prompt injection, jailbreaks, PII leakage, secret leakage, and other malicious content using deterministic rules, returning verdicts and safe redacted text.
      1
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Provides deterministic scanning and detection of prompt injection, jailbreak, data-exfiltration, and system-prompt leaks, with EIP-191 signed attestations and 0G Storage anchoring for verifiable safety reports.
      1
      MIT
    • F
      license
      Not graded
      quality
      B
      maintenance
      Enables auditing an AI agent's guardrails by providing adversarial test prompts and scoring responses against known refusal/guardrail patterns.
      -