Skip to main content
Glama

mcp-eu-ai-act

by io.github.ark-forge

check_compliance

Check whether your project passes or fails each EU AI Act requirement — no arguments, 5 seconds. See exactly which articles you violate (Art. 52 transparency, Art. 11 documentation, Art. 14 human oversight, Art. 15 robustness) and get step-by-step fix instructions for every gap. Call combined_compliance_report() for EU AI Act + GDPR together.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_pathNoPath to the project root. Omit entirely or pass '.' to check the current working directory..
risk_categoryNoEU AI Act risk category: 'minimal', 'limited' (default, fits most AI apps), 'high', or 'unacceptable'.limited

TDQS

A3.9/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses speed (~5 seconds), that it returns pass/fail per requirement, and that it provides fix instructions. However, it incorrectly claims 'no arguments' while the schema defines two optional parameters, and it does not state whether the operation is read-only (though 'check' implies it).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact (three sentences) and front-loaded with the main purpose. The phrase 'no arguments' is inaccurate and wasteful, but otherwise every sentence adds useful context such as specific articles and the alternative combined tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains what results look like (pass/fail, article-level violations, step-by-step fixes), so return values are covered despite no output schema. It does not mention risk_category semantics, but the schema provides that. The tool is sufficiently described for an optional-parameter check tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description does not add param semantics, and its claim of 'no arguments' is misleading given the optional project_path and risk_category parameters. Schema descriptions already cover both parameters, so the description neither helps nor hurts beyond the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool checks EU AI Act compliance, lists specific articles (Art. 52, 11, 14, 15), and mentions fix instructions. It also distinguishes itself from combined_compliance_report for GDPR+AI Act.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly directs users to call combined_compliance_report() for combined EU AI Act + GDPR, implying this tool is for EU AI Act only. It does not mention when to prefer this over gdpr_check_compliance, but the name and the mention of EU AI Act requirements provide sufficient context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All mcp-eu-ai-act toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation2/5

Multiple tools overlap in scope: scan_project, gdpr_scan_project, and combined_compliance_report all perform scanning, while check_compliance, gdpr_check_compliance, and combined_compliance_report all return pass/fail results. The combined tool explicitly replaces the individual scanners, yet they remain available, creating confusion about which to call.

Naming Consistency2/5

Naming conventions are inconsistent: EU AI Act tools use verb-first patterns (generate_report, scan_project), while GDPR tools prefix the law (gdpr_generate_report, gdpr_scan_project). 'combined_compliance_report' breaks the verb_noun pattern entirely, and the placement of 'gdpr' varies inconsistently across tools.

Tool Count3/5

16 tools is on the heavier side for this domain, but the dual EU AI Act + GDPR scope partially justifies the count. However, several tools are redundant (e.g., scan_project vs. combined_compliance_report), inflating the total without adding unique functionality.

Completeness4/5

The tool set covers the compliance lifecycle well: scanning, gap analysis, reporting, templates, roadmap generation, certification, and risk classification. Minor gaps exist (e.g., no tool to manage specific remediation status), but the core workflows are fully supported.

Resources