All recipes

Secure & Govern · Prompt

Seed the risk register

Propose the risks that fit this client, based on their ControlMap data, and pre-score them.

ControlMap
Requires MCPby Greg Brydon · Solutions Engineer

Needs an LLM client connected to ScalePad MCP — Claude Desktop, Cursor, Windsurf or similar. Without it the assistant cannot call the recipe's tools.

User prompt

1 input to fill
Using what ControlMap knows about [CLIENT NAME] (assessment answers, frameworks, existing risks, linked assets), propose risks that genuinely apply to them. Skip anything already in their register or that doesn't fit their environment.

For each risk, give its current impact and likelihood (1 to 5) with a one-line reason, an owner, a department and category (only values from GET /risks/departments and /risks/categories), a business impact statement, and the objectives and action items that relate to it.

Show the register sorted by score. Before you create, update or delete anything, show me exactly what you plan to change in a table and wait for my approval. After approval, create the risks with those values and link them to objectives, assets and action items.

How to work with the ControlMap API (ScalePad MCP):
- Find the client with GET /controlmap/v1/clients/health and use its tenant ID (for example "dundmif") in every request. Some clients have no UUID.
- Send the header Content-Type: application/json on every POST, PUT and PATCH, including searches.
- Use page_size of 50 or less and follow next_cursor. The "fields" parameter is ignored, so responses are large.
- Judge controls by "status", not the "compliant" flag. Objective lists include sub-objectives, so take totals from objective_summary.
- Use framework-level scores and labels. The overall score_label on client health can be wrong.
- Older policy sections may be URL-encoded twice: decode them and use the highest version of each section.
- If a call returns 502 or fails to connect, wait a few seconds and retry once. If it still fails, tell me exactly which data is missing.

When writing to ControlMap:
- Update policies one field per request. review_date must include milliseconds (2027-01-01T00:00:00.000Z) and policy status must be draft, in_progress, in_review or approved.
- Risk scores and treatment can't be changed through the API. A new risk takes one impact and likelihood, which sets inherent, current and target together. List any score or treatment changes for me to make in ControlMap.
- Write evidence request notes to the "notes" field and assignees to "assigned_to".
- Files can't be uploaded through the MCP. Attach a link to where the file lives (SharePoint, Google Drive) and list any files I need to upload in ControlMap.
- Department and risk category must match existing values (GET /risks/departments and /risks/categories).
- Action item effort is capped at 8 hours, so put larger estimates in the description.
- A 500 error can still save part of a change. Read the record back before retrying.

# Seed the risk register

Hook: Pick the ControlMap risk templates that fit this client and pre-score them.

When to use it

Early in onboarding, once scope is known.

What you get

A starter risk register with likelihood, impact, owner and linked objectives. Treatment is set in ControlMap.

Fill in the details

  • [CLIENT NAME]: Client name (e.g. Acme Dental)

Status

Tested against the ControlMap API on October 16, 2026. Only asks for what the API supports.

Makes changes: Claude shows a plan of every create, update or delete and waits for your approval before acting.

GBAuthorGreg BrydonSolutions Engineer · ScalePad

Recipes are starting points. Adapt them to your environment and validate the output before putting one into practice.

Request a recipe

More in Secure & Govern