approve_ai_proposal · ComplyOS MCP: Risk & Policy

WHAT IT DOES

What approve_ai_proposal does on ComplyOS

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

WHY IT NEEDS A POLICY

Why approve_ai_proposal needs a policy

The tool creates or modifies data (approves a proposal record) in a reversible manner. It does not delete data (Destructive), execute arbitrary code (Execute), or move money (Financial). While approval in a compliance context could have downstream consequences, the tool itself only mutates metadata and does not directly enforce compliance outcomes.

From the tool's definition Tool description states "Mutating metadata only: approve an AI proposal record" — this is a create/modify operation (approve/mutating) that changes data state, though explicitly limited to metadata without affecting "compliance truth".

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

approve_ai_proposal Rate-limited

approve_ai_proposal 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": {
    "approve_ai_proposal": {
      "limits": [
        {
          "counter": "approve_ai_proposal_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 ComplyOS, so you can run agents against it safely.

FAQ

Questions about approve_ai_proposal

What does the approve_ai_proposal tool do? +

Mutating metadata only: approve an AI proposal record without changing compliance truth. It is categorised as a Write tool in the ComplyOS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on approve_ai_proposal? +

Register the ComplyOS MCP server in PolicyLayer and add a rule for approve_ai_proposal: 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 ComplyOS. Nothing to install.

What risk level is approve_ai_proposal? +

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

Can I rate-limit approve_ai_proposal? +

Yes. Add a rate_limit block to the approve_ai_proposal 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 approve_ai_proposal completely? +

Set action: deny in the PolicyLayer policy for approve_ai_proposal. 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 approve_ai_proposal? +

approve_ai_proposal is provided by the ComplyOS MCP server (simongonzalezdc/complyos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.