EU AI Act Compliance
Description
EU AI Act compliance for AI agents, grounded in Regulation (EU) 2024/1689 as amended by Regulation (EU) 2026/1744 (Digital Omnibus, in force 27 July 2026). Operative law is the default in every answer; pending changes are opt-in and labelled by source status. Ten deterministic tools, no LLM in the loop, so the same input always returns the same output. euaiact_assess_system takes one normalized system profile and returns separate legal-classification, impact and implementation-readiness blocks with field-level provenance. euaiact_classify_system returns a risk tier (prohibited, high-risk, limited, minimal) from free text or structured signals, naming both the signals it matched and the ones it still needs. The rest cover Annex III and Annex IV, provider and deployer obligations, the Art. 6(3) exception including the profiling carve-out, GPAI systemic risk at the Art. 51 threshold of 10^25 FLOPs, penalties, deadlines, and article lookup with stable EUR-Lex citations. Five resources and
What our measurements say
EU AI Act Compliance is a remote MCP server published at mcp.lexbeam.com. It has been probed 7 times since 9/10/2026. It answered in 7 of them (100.0%), a near-uninterrupted record. Median response time is 410 ms, placing it among the faster endpoints. It offers a narrow, focused set of 10 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Strengths
- Tool names clearly indicate their primary function (e.g., 'classify_system', 'check_deadlines').
- Descriptions provide specific use cases and input types for most tools.
Weaknesses
- Multiple descriptions are truncated (e.g., 'Returns risk classifi', 'structured Digital Omnibus p').
- Lack of explicit error-handling or constraint documentation in tool descriptions.
- Some parameters (e.g., 'structured signals') lack precise definition or type specifications.
euaiact_classify_system— Truncated description cuts off critical output details.euaiact_check_deadlines— Incomplete explanation of 'include_pending_omnibus' parameter.euaiact_get_article— Unclear handling of unsupported article requests.
Verdict
Event narrative
Risk: medium
- 2026-09-10T21:16:35.016Z — era changed from auth-gated to legacy · transition to legacy mode enabled compliance scoring
- 2026-09-11T03:50:39.090Z — complianceScore rose from null to 100 · full regulatory compliance achieved
- 2026-09-11T05:44:28.819Z — smokeOk dropped from true to null · smoke test status became uncertain
Advice
Schema compliance
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
- tools/list schema valid
- inputSchema is valid JSON Schema
- Smoke test passed · last run:
- Cold-start: cold 38ms → warm 43ms (penalty 0ms)
Availability history
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Server build: — → 1.5.0
- Supported versions: — → 2025-11-25
- Era changed: Auth-gated → Legacy
- Added to watch — era: Auth-gated
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/lexbeam-software-eu-ai-act)<a href="https://mcpmetrics.io/servers/lexbeam-software-eu-ai-act"><img src="https://mcpmetrics.io/badge/lexbeam-software/eu-ai-act/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to see