Parametrize a NORMA compliance template with company context and return Markdown. Templates are sourced from the curated corpus (32 in the public subset, 176 more queryable in full). Output begins with a not-legal-advice disclaimer block. Use search_controls first to discover a slug.
AI agents use generate_policy to create or update resources in NORMA MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your NORMA MCP Server environment.
This is a Write operation because it creates new policy documents based on templates and company-supplied parameters. The output is a generated compliance policy document. Severity is medium rather than high because: (1) policies are typically reversible/editable documents, (2) output includes a liability disclaimer, and (3) the tool operates within a bounded compliance template corpus (208 templates total).
From the tool's definition Tool generates and returns policy documents in Markdown format by parameterizing compliance templates with company context. Description explicitly states 'parametrize... and return Markdown,' indicating creation of new output artifacts.
Attacks that exploit this kind of access
Parametrize a NORMA compliance template with company context and return Markdown. Templates are sourced from the curated corpus (32 in the public subset, 176 more queryable in full). Output begins with a not-legal-advice disclaimer block. Use search_controls first to discover a slug. It is categorised as a Write tool in the NORMA MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the NORMA MCP Server MCP server in PolicyLayer and add a rule for generate_policy: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches NORMA MCP Server. Nothing to install.
generate_policy is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the generate_policy rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for generate_policy. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
generate_policy is provided by the NORMA MCP Server MCP server (kynosure-ai/norma-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →