Ansvar: EU Compliance & Legal Intelligence

Start Workflow

start_workflow

Begin a structured workflow selected from the live workflow registry. The registry covers threat and privacy modeling; enterprise, automotive, robot, rail, OT and UAS risk/TARA; DPIA and FRIA; regulatory, medical-device, drone and machinery gap analysis; tender review and audit; document review; SORA authorisation; vulnerability prioritisation; and deferral dossiers. Call list_workflow_types first: it is the authoritative source of exact ids, deliverables, required slots, variants, and availability for this caller. When a fresh registry snapshot is available, this tool's workflow_type input schema carries a caller-authorized enum; otherwise it remains a string rather than silently falling back to a stale catalog. The workflow engine guides the process step by step with quality gates. Each step's questions_for_user is advisory — answerable from context or uploaded documents; only steps returning requires_user_input=true carry the server-enforced human-input gate. Which types you can start is tier-fenced: free and solo include seven types (1 and 2 runs a month) — threat_model, gap_analysis with its gap_analysis_nis2, gap_analysis_dora, gap_analysis_cra and gap_analysis_ai_act variants, and dpia, each reported as JSON or as a watermarked html or pdf — at those tiers the framework argument accepts only nis2, dora, cra or eu_ai_act, and the base gap_analysis needs one of them; Premium adds the rest of the interview-grounded catalog — LINDDUN, the TARA families, FRIA and the jurisdictional DPIA and gap variants, SORA, the drone and OT types, machinery conformity, and enterprise risk — with 5 runs a month; document review, the tender family and adversary tabletop and the DORA ICT-contract and register-of-information variants require Team or Company. MiCA CASP and AMLR readiness are Premium workflows. A start SPENDS a run from the monthly allowance, and on free and solo a cancel does not hand an unused one back — name the workflow_type you intend to the user and get their OK before calling this, and check get_my_capabilities for what is left.

Input Schema

TableJSON Schema

Name	Required	Description
`framework`	No	Regulatory framework the run is scoped to, such as 'nis2', 'dora', 'cra', or 'eu_ai_act'. Free and solo accept only those four, and the base gap_analysis type requires one of them. Empty leaves the workflow's own default in place.
`jurisdictions`	No	ISO-2 codes of the jurisdictions the assessment covers, such as ['SE', 'EU']. Empty leaves the workflow to ask for scope in a later step.
`workflow_type`	Yes	Exact workflow type id from list_workflow_types, such as 'threat_model' or 'gap_analysis_nis2'. When a fresh registry snapshot is available this argument carries an enum of the ids this caller may start; otherwise call list_workflow_types rather than guessing an id from an example. Starting a workflow spends a run from the monthly allowance.
`entity_description`	No	Plain-language description of the organisation or system being assessed, used to ground the workflow's first steps — for example 'a Swedish payments SaaS processing card data for EU merchants'.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedJul 31, 2026

addedInput schema / properties / entity_description / description

Added value: +"Plain-language description of the organisation or system being assessed, used to ground the workflow's first steps — for example 'a Swedish payments SaaS processing card data for EU merchants'."

addedInput schema / properties / framework / description

Added value: +"Regulatory framework the run is scoped to, such as 'nis2', 'dora', 'cra', or 'eu_ai_act'. Free and solo accept only those four, and the base gap_analysis type requires one of them. Empty leaves the workflow's own default in place."

addedInput schema / properties / jurisdictions / description

Added value: +"ISO-2 codes of the jurisdictions the assessment covers, such as ['SE', 'EU']. Empty leaves the workflow to ask for scope in a later step."

addedInput schema / properties / workflow_type / description

Added value: +"Exact workflow type id from list_workflow_types, such as 'threat_model' or 'gap_analysis_nis2'. When a fresh registry snapshot is available this argument carries an enum of the ids this caller may start; otherwise call list_workflow_types rather than guessing an id from an example. Starting a workflow spends a run from the monthly allowance."

First observedJul 31, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only say readOnlyHint=false, destructiveHint=false, openWorldHint=false. The description carries the real behavioral burden and does so richly: it discloses that starting SPENDS a run, that a cancel does not refund runs on free/solo, that questions_for_user is advisory while requires_user_input=true gates are server-enforced, that the workflow_type enum is caller-authorized only when a fresh registry snapshot exists, and that output can be JSON or watermarked html/pdf. This adds substantial context beyond the annotations with no contradiction.

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

Conciseness4/5

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

The description is long and dense — roughly 300 words across several clauses — and is not a model of brevity. However, every sentence earns its place given the tool's complexity: tier-fencing, variant catalogs, run allowances, and advisory-vs-enforced input gates all need to be stated. The core purpose is front-loaded in the first sentence, and the parameter/semantic details follow logically. Slightly over-length but justified; not padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no elaboration. The description covers prerequisites (list_workflow_types first, get_my_capabilities for allowance), tier restrictions, run-allocation consequences, the input-gate model, and output formats. For a stateful, tier-fenced workflow launcher with side effects, everything an agent needs to call it correctly is present. Nothing material is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds genuine value: it explains that workflow_type must come from list_workflow_types rather than guessing from an example, that the enum is caller-authorized and may degrade to a string, and that the base gap_analysis type requires a framework. It also clarifies the framework argument accepts only nis2/dora/cra/eu_ai_act on free/solo. This exceeds baseline by tying parameters to the live-registry semantics.

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 begins with a specific verb+resource ('Begin a structured workflow selected from the live workflow registry') and enumerates the exact catalog covered — threat/privacy modeling, risk/TARA, DPIA/FRIA, gap analysis, SORA, etc. It distinguishes itself from siblings like list_workflow_types (the authoritative id source) and list_workflows. An agent can clearly tell what this tool does and what it is not.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly instructs 'Call list_workflow_types first' and names get_my_capabilities as the check for remaining allowance, and cancel_workflow as the companion. It gives tier-fencing rules (free/solo seven types, Premium adds the interview-grounded catalog, Team/Company required for document review/tender/adversary), which routes the agent to the correct usage path. It even mandates getting user OK before calling — explicit when-to-use guidance with named alternatives.

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

All Ansvar: EU Compliance & Legal Intelligence tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.