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, 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, and full compliance reports.
10 Tools
Tier | Tool | What it does |
Scanning |
| Scan Python code string for all 6 EU AI Act articles |
Scanning |
| Read and scan a single Python file |
Scanning |
| Recursively scan all .py files in a directory |
Analysis |
| Deep analysis via local fine-tuned model (Ollama) |
Analysis |
| Detect prompt injection attacks (15 patterns) |
Analysis |
| Classify tools by EU AI Act risk level |
Remediation |
| Generate trust layer integration code |
Remediation |
| Get article-specific fix recommendations |
Documentation |
| Technical explanation of EU AI Act articles |
Documentation |
| Full markdown compliance report |
Supported Frameworks
LangChain, CrewAI, AutoGen, OpenAI, Haystack, LlamaIndex, Semantic Kernel, and generic RAG pipelines.
Install
pip install air-blackbox-mcpClaude 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 10 tools will appear automatically.
Cursor Setup
Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"air-blackbox": {
"command": "python3",
"args": ["-m", "air_blackbox_mcp"]
}
}
}Usage Examples
In Claude Desktop 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 my project at ~/myproject"
"Classify the risk level of
send_email"
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 — 18+ regex patterns across 6 EU AI Act articles
Analyzes — local fine-tuned model catches what regex misses
Remediates — generates working code to fix findings
Verifies — checks for prompt injection with 15 weighted patterns
Classifies — maps tools to EU AI Act risk levels
Documents — produces full compliance reports
Links
AIR Blackbox Scanner — the CLI scanner
airblackbox.ai — project homepage
EU AI Act — the regulation
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.