mcp-eu-ai-act
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| quick_risk_classA | 30-second deterministic multi-jurisdiction AI risk classification across EU AI Act, NIST AI RMF, ISO/IEC 42001, OECD, Singapore Model AI Governance, GDPR, and sector-specific overlays (HIPAA, NYC AEDT, Colorado SB 24-205). No LLM call. Same inputs always produce same outputs. Use this for quick orientation before deeper analysis. |
| classify_annex3A | Deep Annex III classification using Claude (Anthropic) with full EU AI Act regulatory context. Maps your product against all 8 Annex III high-risk categories + Article 50 transparency + GPAI Article 53 + GPAI provider/deployer reasoning. Returns 5 priority remediation actions tailored to your stack. ~60 seconds (LLM-powered). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one is a deep, LLM-powered classification focused on EU AI Act Annex III, while the other is a deterministic, multi-jurisdiction quick risk assessment. There is no overlap or ambiguity.
Both tool names follow a consistent verb_noun pattern using snake_case: classify_annex3 and quick_risk_class. The naming convention is uniform and predictable.
With only 2 tools, the server is minimal but appropriately scoped for a specific domain (AI Act risk classification). Each tool serves a distinct role, so the count is reasonable, though slightly low for broader coverage.
The tools cover deep Annex III classification and quick multi-jurisdiction orientation, but lack other potentially useful operations such as retrieving detailed category information, updating classifications, or generating reports. This creates notable gaps for comprehensive workflows.