Returns your current governance coverage gaps relative to the described action.\n\n
AI agents call derive_controls to retrieve information from Governance Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries governance/compliance state and identifies gaps, which is a read operation with no side effects. It does not create, modify, delete, or execute actions; it only retrieves and analyzes existing governance posture data. Even if misused by an AI agent, it cannot directly damage systems, move funds, or irreversibly change state. The low severity reflects minimal blast radius for accidental misuse.
From the tool's definition Tool description states it "Returns your current governance coverage gaps" — a retrieval operation that analyzes and reports data without modifying, deleting, or executing external actions.
Attacks that exploit this kind of access
Returns your current governance coverage gaps relative to the described action.\n\n. It is categorised as a Read tool in the Governance Mcp MCP Server, which means it retrieves data without modifying state.
Register the Governance MCP server in PolicyLayer and add a rule for derive_controls: 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 Governance Mcp. Nothing to install.
derive_controls is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the derive_controls 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 derive_controls. 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.
derive_controls is provided by the Governance MCP server (@mima-ai/governance-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
derive_controls is one line of Governance's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →