Aiact MCP server
Scan codebases for AI usage, classify risk, generate EU AI Act compliance reports.
0 stars53 downloads/wk
Reviews
Write oneNobody has reviewed Aiact yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Aiact tools (4)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
classify_systemClassify the EU AI Act risk level for a specific AI system based on its type and use case. Helps determine which obligations apply.
generate_inventoryGenerate a formal EU AI Act inventory document for a project. Produces a structured inventory suitable for compliance records, covering all detected AI systems with risk classifications and documentation requirements.
quick_checkQuick scan to count AI systems in a project without full compliance analysis. Faster than scan_project.
scan_projectScan a project directory for AI system usage and generate an EU AI Act compliance report. Detects LLM APIs (OpenAI, Anthropic, Google, Mistral, etc.), ML frameworks (PyTorch, TensorFlow, scikit-learn), computer vision, NLP, embeddings, and more. Classifies risk level and identifies compliance gaps against the August 2, 2026 deadline.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan11 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 168 days ago8/15
- Maintainer identityregistry namespace matches repository owner6/10
How Aiact compares
Against every graded Security MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 78/100
- higher than 61% of 915 Security servers
- Tools
- 4
- the typical Security server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 53
- more than 44% of 248 Security servers with a package
What its tools let an agent do: 3 read · 1 create
Install Aiact in Claude Code, Cursor or VS Code
Runs npx -y gridwork-aiact on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add aiact -- npx -y gridwork-aiact
What the publisher says
From the Aiact repository's README, as published. We do not edit it. Read it on GitHub
gridwork-aiact
MCP server that scans codebases for AI system usage and generates EU AI Act compliance reports.
EU AI Act high-risk deadline: August 2, 2026.
What it does
- Scans project files for AI libraries, APIs, and frameworks
- Detects 30+ AI systems: OpenAI, Anthropic, Google, PyTorch, TensorFlow, HuggingFace, LangChain, and more
- Classifies risk level per EU AI Act (unacceptable / high / limited / minimal)
- Identifies compliance gaps against Annex III categories
- Generates formal inventory documents for compliance records
- Counts days until the August 2, 2026 deadline
Install
npx gridwork-aiactMCP tools
Claude Desktop config
{
"mcpServers": {
"gridwork-aiact": {
"command": "npx",
"args": ["-y", "gridwork-aiact"]
}
}
}License
MIT — Gridwork
Nothing above is checked by us. What we check is on the safety report.
Aiact: common questions
- Is Aiact MCP server safe?
- Mostly: it is graded B (78/100). Read the Aiact safety report
- How do I install Aiact?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Aiact need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Aiact maintained?
- The last commit was 206 days ago (2026-04-12). The latest release is v1.0.0.
- What can I use instead of Aiact?
- Servers from other publishers that do the same job: Air Blackbox MCP server, OpenQR MCP server and MCP ZAP Server MCP server.
- How does Aiact compare with other Security MCP servers?
- safety score 78/100 (higher than 61% of 915 Security servers); tools 4 (the typical Security server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Aiact
Same job from other publishers: the closest match first, then the best rated.
- Air BlackboxEU AI Act compliance scanner for Python AI agents — scan, analyze, and remediatenot reviewedGrowingA
- OpenQRGenerate, edit and track dynamic (editable) QR codes with scan analytics. Hosted MCP and REST API.not reviewedGrowingB
MCP ZAP ServerSafe, self-hosted ZAP operator for guided AI security scans and reports.not reviewedGrowingB- mcp-auditScan, enumerate, and risk-score every MCP server configured on your machine.not reviewedGrowingA
- Barcode ScannerScan and generate barcodes and QR codes.not reviewedGrowingA