register_system · Governance MCP: Risk & Policy

WHAT IT DOES

What register_system does on Governance Mcp

AI agents use register_system to create or update resources in Governance Mcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Governance Mcp environment.

WHY IT NEEDS A POLICY

Why register_system needs a policy

This tool creates new data entries (system registration and risk assessment records) in a governance ledger. This is a reversible Write operation—records can be updated, corrected, or removed later. It is not Read (retrieves data), Execute (runs arbitrary code), Destructive (irreversibly deletes), or Financial.

From the tool's definition Tool description states 'Register an AI system' and 'Creates an Art. 9 risk assessment', indicating it adds new records to a governance ledger.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

register_system Rate-limited

register_system stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "register_system": {
      "limits": [
        {
          "counter": "register_system_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Governance Mcp, so you can run agents against it safely.

FAQ

Questions about register_system

What does the register_system tool do? +

Register an AI system in the Mima governance ledger. Creates an Art. 9 risk assessment. It is categorised as a Write tool in the Governance Mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on register_system? +

Register the Governance MCP server in PolicyLayer and add a rule for register_system: 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.

What risk level is register_system? +

register_system is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit register_system? +

Yes. Add a rate_limit block to the register_system 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.

How do I block register_system completely? +

Set action: deny in the PolicyLayer policy for register_system. 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.

What MCP server provides register_system? +

register_system 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.

// THE FULL RECORD

register_system 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 →