air-blackbox-mcp
Enables automated EU AI Act compliance scanning, risk classification, and remediation for CrewAI multi-agent systems.
Provides tools for scanning LangChain applications for EU AI Act compliance and generating trust layer integration code.
Integrates with local Ollama instances to perform deep AI-powered compliance analysis and detect prompt injection attacks using fine-tuned models.
Facilitates EU AI Act compliance scanning, vulnerability detection, and risk classification for OpenAI-based applications and integrations.
AIR Blackbox MCP Server
EU AI Act compliance scanning for Claude Desktop, Claude Code, Cursor, and any MCP-compatible client.
Unlike other compliance scanners that only report problems, AIR Blackbox also remediates — generating working code fixes, trust layer integrations, GDPR compliance checks, bias analysis, and full compliance reports. Under the hood, the scanning feeds into air-trust, a cryptographic audit chain (HMAC-SHA256) with Ed25519 signed handoffs that ensures compliance data integrity.
14 Tools (10 base + 4 SDK-powered)
Tier | Tool | What it does | Requires SDK |
Scanning |
| Scan Python code string for all 6 EU AI Act articles | No |
Scanning |
| Read and scan a single Python file | No |
Scanning |
| Recursively scan all .py files in a directory | No |
Analysis |
| Deep analysis via local fine-tuned model (Ollama) | No |
Analysis |
| Detect prompt injection attacks (15 patterns) | No |
Analysis |
| Classify tools by EU AI Act risk level | No |
Remediation |
| Generate trust layer integration code | No |
Remediation |
| Get article-specific fix recommendations | No |
Documentation |
| Technical explanation of EU AI Act articles | No |
Documentation |
| Full markdown compliance report | No |
GDPR |
| GDPR-specific compliance scan | Yes |
Bias |
| Bias and fairness analysis | Yes |
Validation |
| Validate agent actions before execution (Article 14) | Yes |
History |
| View past scans, trends, and compliance scores | Yes |
Supported Frameworks
LangChain, CrewAI, AutoGen, OpenAI, Haystack, LlamaIndex, Semantic Kernel, Google ADK, Claude Agent SDK, and generic RAG pipelines.
Installation
Basic (10 tools, no SDK features)
pip install air-blackbox-mcpWorks standalone with just the lightweight built-in scanner.
Full (14 tools with GDPR, bias, validation, and history)
pip install air-blackbox-mcp[full]Installs the full air-blackbox SDK (v1.6.3+) for advanced compliance features.
Claude Desktop Setup
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"air-blackbox": {
"command": "python3",
"args": ["-m", "air_blackbox_mcp"]
}
}
}Restart Claude Desktop. The 14 tools will appear automatically.
Claude Code / Cursor Setup
Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"air-blackbox": {
"command": "python3",
"args": ["-m", "air_blackbox_mcp"]
}
}
}Or add to .claude/mcp.json for Claude Code.
Usage Examples
In Claude Desktop, Claude Code, or Cursor, just ask:
"Scan this code for EU AI Act compliance"
"Add a trust layer to this LangChain agent"
"Check this text for prompt injection"
"What does Article 12 require?"
"Generate a compliance report for ~/myproject"
"Classify the risk level of
send_email""Scan this code for GDPR issues" (requires full SDK)
"Check for bias in this AI model code" (requires full SDK)
"Can my agent call this shell function?" (requires full SDK)
"Show me my compliance trends" (requires full SDK)
SDK Features (Optional)
The full air-blackbox SDK unlocks 4 additional tools:
GDPR Scanning (
scan_gdpr)Personal data handling without consent
Data retention and erasure policies
Cross-border transfer safeguards
Data processing agreements
Bias Analysis (
scan_bias)Disparate impact risk detection
Protected attribute handling
Training data bias indicators
Fairness metric awareness
Action Validation (
validate_action)Pre-execution approval gates (Article 14)
ConsentGate policy enforcement
Risk-based action filtering
Audit trail generation
Compliance History (
compliance_history)Track past scan results
Analyze compliance trends
Export audit trails
Monitor improvement over time
Optional: Deep Analysis with Ollama
For AI-powered analysis beyond regex patterns:
# Install Ollama
brew install ollama
# Pull the fine-tuned compliance model
ollama pull air-compliance-v2
# The analyze_with_model tool will automatically use itWhat Makes This Different
Other MCP compliance tools only scan. AIR Blackbox:
Scans + Remediates — finds issues across 6 EU AI Act articles AND generates working code fixes
Analyzes deeply — regex patterns + AI-powered model analysis + prompt injection detection (15 patterns)
Validates before execution — pre-approval gates and risk classification for agent actions (Article 14)
Tracks compliance — GDPR checks, bias analysis, full reports, and historical trend monitoring (SDK)
Architecture
The server uses a smart fallback pattern:
Try SDK first — If
air-blackbox>=1.6.0is installed, use the full compliance engineFall back gracefully — If SDK isn't installed, use the lightweight built-in scanner
No breaking changes — Works with just
pip install air-blackbox-mcp(basic mode)Opt-in superpower — Install
[full]to unlock advanced features
This means the MCP server works standalone, but gets dramatically more powerful when the SDK is present.
Part of AIR Blackbox
This MCP server is part of the AIR Blackbox ecosystem:
air-trust on PyPI — the cryptographic audit chain that backs compliance scanning
air-blackbox on PyPI — the full compliance SDK and CLI scanner
airblackbox.ai — the project homepage and docs
Links
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/airblackbox/air-blackbox-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server