Log inSubmit server
Air Blackbox MCP logo

Air Blackbox MCP

by airblackbox

Scans Python AI-agent code for EU AI Act issues and generates remediation, reports, and optional GDPR, bias, and validation checks.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Air Blackbox MCP

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "airblackbox-air-blackbox-mcp": {
      "command": "uvx",
      "args": [
        "air-blackbox-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

uvx air-blackbox-mcp

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 1mo ago.

Overview

The airblackbox/air-blackbox-mcp MCP server scans Python AI-agent code for issues across six EU AI Act articles and can generate remediation code. It provides built-in rule-based tools for code, file, project, prompt-injection, risk, reporting, and article analysis, with optional SDK tools for GDPR, bias, action validation, and compliance history. Install the base package for 10 tools or the full extra for all 14; use it with Claude Desktop, Claude Code, Cursor, or another MCP-compatible client. Reach for it when compliance findings need code fixes, provenance, or pre-execution checks rather than a scan-only result.

Use cases

  • Scan a Python agent project for EU AI Act findings
  • Generate code fixes for identified compliance issues
  • Detect prompt injection patterns in agent inputs
  • Validate agent actions before execution
  • Track compliance scores and historical trends

Key features

  • Scans code across six EU AI Act articles
  • Generates article-specific remediation suggestions
  • Detects prompt injection across 15 patterns
  • Classifies agent tools by risk level
  • Supports optional GDPR, bias, validation, and history tools
  • Includes result provenance metadata

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

21/21 checks healthy over the last 91d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 5d ago via OSV.dev · air-blackbox-mcp (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars3Stargazers on the source repository.
Last commit24d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity5 viewsConfig copies, upvotes, and views on AllMCPs.

How Air Blackbox MCP works

What airblackbox/air-blackbox-mcp MCP server does

The airblackbox/air-blackbox-mcp MCP server exposes compliance checks for Python applications that use AI-agent frameworks and model APIs. It scans code strings, individual Python files, or complete directories, then reports findings related to six EU AI Act articles. Supported frameworks include LangChain, CrewAI, AutoGen, OpenAI, Haystack, LlamaIndex, Semantic Kernel, Google ADK, Claude Agent SDK, and generic RAG pipelines.

The server is designed to go beyond detection. Its remediation tools can suggest article-specific changes and generate trust-layer integration code. It can also explain EU AI Act articles and produce a Markdown compliance report. Prompt injection checks cover 15 patterns, while risk classification evaluates tools against EU AI Act risk levels.

How it works

The base tools always use the built-in rule-based scanner. They do not switch to the SDK when the SDK happens to be installed. The optional GDPR, bias, action-validation, and compliance-history tools always use the air-blackbox SDK and return an explicit installation error if that dependency is unavailable.

Results include provenance describing the engine, scanner version, ruleset identifier, ruleset version, and SDK version when applicable. This makes results easier to compare: reports produced by the same engine and ruleset version come from identical rules, while changes in those values provide context for interpreting differences.

For deeper analysis, analyze_with_model can use the locally installed Ollama model air-compliance-v2. Ollama is optional and is not required for the built-in scanner. The MCP implementation supports MCP SDK 1.x and 2.x by selecting the appropriate server class at runtime.

Setup and configuration

Install the base distribution with:

Terminal
pip install air-blackbox-mcp

This provides the ten tools that do not require the full SDK. To enable GDPR scanning, bias analysis, action validation, and compliance history, install:

Terminal
pip install air-blackbox-mcp[full]

The full extra installs the air-blackbox SDK with a declared range of >=1.13,<2. Launch the server over stdio with python3 -m air_blackbox_mcp. Claude Desktop and Cursor configurations use that command with no server URL or credential setting.

Tools and capabilities

The airblackbox/air-blackbox-mcp MCP server includes these base capabilities:

  • Scan Python strings, files, or directories with scan_code, scan_file, and scan_project.
  • Analyze code with an optional local Ollama model.
  • Detect prompt injection and classify agent-tool risk.
  • Generate trust-layer code and article-specific fix suggestions.
  • Explain EU AI Act articles and create full Markdown compliance reports.

With the full SDK installed, it additionally supports GDPR checks for consent, retention, erasure, transfers, and processing agreements; bias analysis covering disparate impact, protected attributes, training-data indicators, and fairness metrics; action validation with approval gates and risk filtering; and historical scan trends, scores, and audit-trail exports.

Limitations and notes

The server targets Python code and the frameworks listed in its documentation. The base installation does not provide the four SDK-powered tools. Ollama analysis also requires a separate Ollama installation and the air-compliance-v2 model. Results should therefore be interpreted with their reported provenance and installed feature tier in mind.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Air Blackbox MCP

Run `pip install air-blackbox-mcp` for the base ten tools, or `pip install air-blackbox-mcp[full]` for all 14 tools.

Yes. Add a server entry using `python3` with `-m air_blackbox_mcp` as its argument, then restart Claude Desktop.

The base scanning tools do not require it. GDPR scanning, bias analysis, action validation, and compliance history require the full SDK installation.

Yes. The `analyze_with_model` tool can use the local `air-compliance-v2` model after Ollama is installed and that model is pulled.

Related MCP servers

All in Security All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewAir Blackbox MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/airblackbox-air-blackbox-mcp?style=directory)](https://allmcps.com/mcp/airblackbox-air-blackbox-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/airblackbox-air-blackbox-mcp"><img src="https://allmcps.com/api/badge/airblackbox-air-blackbox-mcp?style=directory" alt="Air Blackbox MCP on AllMCPs" /></a>