Schema | ai-act-mcp

ai-act-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`AI_ACT_SLM_MODEL`	No	Model name for local Ollama classification.	llama3.2
`AI_ACT_CLASSIFIER`	No	Backend for classification: keyword (default, deterministic, offline), local (Ollama, fully offline), or host (via MCP sampling).	keyword
`AI_ACT_OLLAMA_URL`	No	URL of the Ollama server for local classification.	http://localhost:11434
`AI_ACT_SLM_TIMEOUT_MS`	No	Timeout in milliseconds for local model before falling back to keyword classifier.	30000

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": true }

Functions exposed to the LLM to take actions

Name	Description
classify_riskA	Classify an AI system under the EU AI Act risk tiers (prohibited / high / limited / minimal) from a plain-English description of what it does and who it affects. Returns the likely tier with cited articles and Annex III categories. Informational triage, not legal advice.
check_obligationsA	List the concrete EU AI Act obligations for a given risk tier and role (provider or deployer), with article citations. Set is_gpai true if you also provide a general-purpose AI model.
next_deadlinesA	Return the EU AI Act compliance timeline, optionally highlighting the date relevant to a given risk tier.
scan_repoA	Scan a local repository path for the documentation artifacts the AI Act expects (model card, data governance, risk management, logging, human oversight, transparency notices) and report pass/warn/fail per artifact.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/a2welt/ai-act-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server