Skip to main content
Glama
mimaworks

mimaworks/governance-mcp

Official
by mimaworks

register_system

Create EU AI Act Art. 9 risk assessment records for AI systems before they process EU personal data. Register systems during design or deployment to map required governance controls.

Instructions

Register an AI system in the Mima governance ledger. Creates an Art. 9 risk assessment record — required once per AI system before it processes EU persons under the EU AI Act.

Use this during design reviews or architecture discussions when a new AI system is being planned or has just been deployed:

  • "We're adding a loan scoring model to production"

  • "This new hiring algorithm needs to be registered"

  • "Register the content moderation system we just deployed"

Pass dry_run=true to preview which controls this registration would earn without writing anything to the ledger. Use this before the real call to confirm the payload is correct.

Returns the record_id and mapped controls (e.g. EUAIA_ART9, ISO42001_6.1). In dry-run mode, record_id is the nil UUID — a clear signal nothing was written.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dry_runNoIf true, preview which controls this registration would earn without writing to the ledger. record_id in the response will be the nil UUID. Use this before the real call.
risk_levelYes'high' = Annex III system requiring full Art. 9 documentation. 'medium' = limited risk, transparency obligations apply. 'low' = minimal risk, no mandatory requirements.
environmentNoDeployment environment. Defaults to 'production'.
system_nameYesUnique identifier for the AI system. Must match what developers pass to mima.attest(system_name=…). Use lowercase with hyphens, e.g. 'loan-scoring-v2'.
risk_summaryYesWhy this system is classified at this risk level. Write a complete sentence. Example: 'This system scores loan applications for EU consumers under Annex III §(e). Human review is mandatory for scores below 600.'
system_versionNoOptional version string, e.g. 'v2.1.0'. Auditors use this to track change events.
intended_purposeYesUse case, target population, and deployment scope. Auditors check this against Annex IV §1. Example: 'Predicts credit default probability for retail loan applicants aged 18-75 in the EU. Assists (does not replace) manual underwriter assessment.'
technical_doc_urlNoURL to Annex IV technical documentation. Must be a live URL.
training_data_urlNoURL to training dataset specification and lineage.
annex_iii_categoryNoThe Annex III category for high-risk systems. Required when risk_level is 'high'. Options: biometric_identification, critical_infrastructure, education_vocational, employment_management, essential_services, law_enforcement, migration_border, justice_democratic.
responsible_personYesEmail of the named person accountable for this system under Art. 14. Must be a real individual, not a team alias.
art5_self_assessmentYesSet true to certify this system does not engage in practices prohibited under Art. 5 (subliminal manipulation, social scoring, real-time biometric identification in public spaces, etc.). Required field — do not set to true without confirming with the system owner.
Behavior4/5

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

With no annotations provided, the description bears full responsibility for disclosing behavior. It explicitly notes that the real call writes a ledger entry while dry_run=true 'preview[s] which controls this registration would earn without writing anything' and that the nil UUID signals no write occurred. It also discloses that registration is mandatory and returns record_id and mapped controls. This goes beyond minimal disclosure, though it does not discuss permissions or irreversibility.

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 well-structured: it opens with a clear purpose, then gives usage context, example utterances, dry-run guidance, and return values in a logical, front-loaded order. Every sentence contributes unique information, and the bullet-point examples make it easy to scan. It is appropriately sized for the tool's complexity.

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 covers the essential context for an AI agent: when to invoke, what it does, how dry-run works, and what the response contains (record_id and mapped controls). Since there is no output schema, this return-value disclosure is valuable. It could add more about failure modes or prerequisites, but for a registration tool with 100% schema coverage, it is sufficiently complete.

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 need to explain each parameter, and it adds minimal extra meaning beyond the schema—mainly reinforcing dry_run's purpose, which is already described in the schema. The schema itself carries the parameter semantics, so the description neither detracts nor significantly augments.

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's purpose: 'Register an AI system in the Mima governance ledger. Creates an Art. 9 risk assessment record.' This is a specific verb+resource pair that differentiates it from sibling tools like list_systems or derive_controls, and it includes the regulatory context (EU 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?

The description explicitly says when to use it: 'during design reviews or architecture discussions when a new AI system is being planned or has just been deployed' and provides realistic example utterances. It also explains the dry_run workflow, but it does not explicitly mention when not to use it or point to alternative tools, though the guidance is clear enough without exclusions.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mimaworks/governance-mcp'

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