scan_codeLABSCO SUMMARY
Compliance scanning that also writes the change, with every result labelled by the rules that produced it.
Which engine runs is fixed per tool rather than a runtime fallback, and each machine-readable result carries a provenance block naming the engine and a content hash of the active ruleset. That is what makes two reports comparable — same engine and ruleset version means byte-identical rules, and a diff between them is meaningful.
What it is
An MCP server that reads Python source for EU AI Act compliance problems and produces remediation rather than just findings — trust-layer integration code, article-specific fixes, and a full markdown report. It recognises LangChain, CrewAI, AutoGen, OpenAI, Haystack, LlamaIndex, Semantic Kernel, Google ADK, the Claude Agent SDK and generic RAG pipelines.
What you get
- scan_code, scan_file and scan_project — a code string, one file, or every .py file under a directory, checked against all six articles
- analyze_with_model — deeper analysis through a local fine-tuned model served by Ollama
- check_injection and classify_risk — prompt-injection detection across 15 patterns, and tools classified by EU AI Act risk level
- add_trust_layer and suggest_fix — generated trust-layer integration code, and article-specific recommendations for what to change
- explain_article and generate_compliance_report — a technical reading of an article, and a full markdown report over a project
- scan_gdpr and scan_bias — consent, retention, cross-border transfer and processing-agreement checks, and disparate-impact and protected-attribute analysis
- validate_action and compliance_history — pre-execution approval gates under Article 14, and past scans with their trend
Requirements
pip install air-blackbox-mcp gives the ten built-in tools with no other dependency; the client runs python3 -m air_blackbox_mcp over stdio. The last four — scan_gdpr, scan_bias, validate_action and compliance_history — always run through the air-blackbox SDK, so they need pip install air-blackbox-mcp[full] and return an explicit error without it. analyze_with_model needs Ollama with the air-compliance-v2 model pulled.
Setup effort
One command — pip install air-blackbox-mcp
USE CASES
01
Checking a codebase before an audit
Scan the whole project, then turn the findings into a markdown compliance report.
02
Fixing what a scan found
Get article-specific recommendations for the flagged code and generate the trust-layer integration.
03
Hardening an agent's inputs
Check incoming text against the injection patterns and classify the tools it can reach by risk level.
04
Adding a human gate before an action
Validate the agent's proposed action against the approval policy before it executes.
05
Understanding what an article requires
Read the technical explanation of the article behind a finding.
14 tools
Listed in project docs. Your client may show a different list.
scan_filescan_projectanalyze_with_modelcheck_injectionclassify_riskadd_trust_layersuggest_fixexplain_articlegenerate_compliance_reportscan_gdprscan_biasvalidate_actioncompliance_historyBEFORE YOU INSTALL
What to know first
Tools you get
14 tools named in the project's documentation.
Requires
python3 on PATH
Where it runs
All 3 documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install air-blackbox-mcpMCP Clients
Claude Desktop, Cursor, Claude Code
JSON
{
"mcpServers": {
"air-blackbox": {
"command": "python3",
"args": [
"-m",
"air_blackbox_mcp"
]
}
}
}
