eu-ai-act-mcp

Get Obligations by Role and Risk Level

euaiact_get_obligations

Read-onlyIdempotent

Retrieve EU AI Act compliance obligations for providers or deployers by risk level, role, and optional filters to identify applicable rules quickly.

Instructions

Returns specific compliance obligations for providers or deployers based on AI system risk level.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`role`	Yes	Provider or deployer role
`risk_level`	Yes	AI system risk level. Use 'gpai' for general-purpose AI model obligations (Art. 51-56).
`filter_keyword`	No	Optional keyword filter for obligations
`annex_iii_point`	No	If high_risk_source is annex_iii, the Annex III point number. Point 2 has special Art. 49/27 treatment.
`high_risk_source`	No	For high-risk systems, whether classification comes from Annex III/Art. 6(2), Annex I/Art. 6(1), or is unknown	unknown
`gpai_model_placed_on_market_before_2025_08_02`	No	For GPAI providers, whether the model was placed on the market before 2 August 2025, triggering the Art. 111(3) transition to 2 August 2027.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`role`	Yes
`penalties`	Yes
`risk_level`	Yes
`lexbeam_url`	No
`obligations`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv1.3.0Jun 21, 2026

addedInput schema / properties / annex_iii_point

Added value: +{
+  "description": "If high_risk_source is annex_iii, the Annex III point number. Point 2 has special Art. 49/27 treatment.",
+  "maximum": 8,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / gpai_model_placed_on_market_before_2025_08_02

Added value: +{
+  "description": "For GPAI providers, whether the model was placed on the market before 2 August 2025, triggering the Art. 111(3) transition to 2 August 2027.",
+  "type": "boolean"
+}

addedInput schema / properties / high_risk_source

Added value: +{
+  "default": "unknown",
+  "description": "For high-risk systems, whether classification comes from Annex III/Art. 6(2), Annex I/Art. 6(1), or is unknown",
+  "enum": [
+    "annex_iii",
+    "annex_i",
+    "unknown"
+  ],
+  "type": "string"
+}

First observedv1.1.5Jun 14, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint and idempotentHint, and the description does not contradict these. However, the description adds little behavioral detail beyond what annotations provide—it doesn't mention pagination, filtering nuances, or conditional parameter behaviors. The bar is lower with annotations, so a 3 is appropriate.

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

Conciseness5/5

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

The description is a single, well-structured sentence that front-loads the core purpose. It contains no filler or redundant information, making it highly concise and easy to parse.

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?

With an output schema and rich input schema, the description covers the essential context. It could mention conditional parameter relationships (e.g., high_risk_source relevant only for high-risk), but the schema handles those details. Overall, the description is adequate for agent invocation.

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?

The input schema provides 100% coverage with descriptions for all 6 parameters, including complex ones like gpai_model_placed_on_market_before_2025_08_02. The tool description adds no extra parameter semantics beyond the schema, so baseline 3 is warranted.

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 verb ('returns'), the resource ('specific compliance obligations'), and the scope ('for providers or deployers based on AI system risk level'). It distinguishes this tool from siblings like euaiact_classify_system and euaiact_get_article by focusing on obligations retrieval rather than classification or raw article text.

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?

The description provides clear context on when to use the tool: when you need obligations for a given role and risk level. It does not explicitly mention alternatives or exclusions, but the input criteria are defined, giving the agent clear guidance on matching user intent to this tool.

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

Deploy Server