Aiact

io.github.thegridworkPublished by GitHub account thegridworkv1.0.0Updated Oct 24, 2026

Scan codebases for AI usage, classify risk, generate EU AI Act compliance reports.

VerifiedSTDIODesktop onlyDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

Scans a local codebase for AI libraries and APIs, classifies EU AI Act risk levels, and generates compliance inventory reports.

What you can do
  • Scan project files for AI libraries, APIs and frameworks, detecting 30+ AI systems
  • Classify each detected system by EU AI Act risk level (unacceptable, high, limited, minimal)
  • Identify compliance gaps against Annex III categories
  • Generate a formal EU AI Act inventory document for compliance records
  • Run a fast count of AI systems without full analysis, and count days until the August 2, 2026 deadline
When to use it
Useful when you need to know which AI components a codebase relies on and how they map to EU AI Act risk categories, or when preparing compliance inventory documentation ahead of the August 2026 high-risk deadline.
Requirements
Runs as a local process over stdio, launched with npx from the npm package gridwork-aiact; Node.js and network access for the package download are needed. No accounts, API keys or environment variables are declared.
Before you install
It reads project files on the machine where it runs, so point it only at codebases you are comfortable having scanned. Its risk classifications and gap findings are generated output and should be reviewed by a qualified person before being used as compliance records.

Installation

In SourceWeft

  1. Open Aiact in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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

bash
npx gridwork-aiact

MCP tools

ToolDescription
scan_projectFull scan with risk classification and compliance gap analysis
quick_checkFast count of AI systems without full analysis
generate_inventoryFormal EU AI Act inventory document
classify_systemClassify risk for a specific AI system by use case

Claude Desktop config

json
{  "mcpServers": {    "gridwork-aiact": {      "command": "npx",      "args": ["-y", "gridwork-aiact"]    }  }}

License

MIT — Gridwork

Source: README.md at commit 329906d

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.