apply_proposal · Metis Public Health MCP: Risk & Policy

WHAT IT DOES

What apply_proposal does on Metis Public Health

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

WHY IT NEEDS A POLICY

Why apply_proposal needs a policy

The tool appears to apply or commit a proposal to the user's local knowledge base, which is a Write operation (creates or modifies data reversibly). It could be Destructive if it overwrites existing proposals irreversibly, but the name suggests commitment rather than destruction. High severity is justified because misuse could corrupt the user's research data or commit unintended changes to their indexed library.

From the tool's definition Tool name 'apply_proposal' suggests executing or committing a proposal. Sibling tools like 'add_journal_entry', 'add_memory_entry', 'add_tracked_file', and 'approve_proposal' indicate this server handles persistent data modifications.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

apply_proposal Rate-limited

apply_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": {
    "apply_proposal": {
      "limits": [
        {
          "counter": "apply_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 Metis Public Health, so you can run agents against it safely.

FAQ

Questions about apply_proposal

What does the apply_proposal tool do? +

apply_proposal. It is categorised as a Write tool in the Metis Public Health MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on apply_proposal? +

Register the Metis Public Health MCP server in PolicyLayer and add a rule for apply_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 Metis Public Health. Nothing to install.

What risk level is apply_proposal? +

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

Can I rate-limit apply_proposal? +

Yes. Add a rate_limit block to the apply_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 apply_proposal completely? +

Set action: deny in the PolicyLayer policy for apply_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 apply_proposal? +

apply_proposal is provided by the Metis Public Health MCP server (sveritg/metis_ph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.