log_agent_run · Metis Public Health MCP: Risk & Policy

WHAT IT DOES

What log_agent_run does on Metis Public Health

AI agents use log_agent_run 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 log_agent_run needs a policy

The name implies logging or recording information about an agent run, which is a Write operation (creating a log entry). However, the empty description significantly lowers confidence. Based on sibling tools like 'add_journal_entry' and 'add_memory_entry', this server pattern uses 'add_*' for writes, but 'log_*' similarly implies persisting data.

From the tool's definition Tool name 'log_agent_run' suggests writing/recording agent execution data; description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

log_agent_run Rate-limited

log_agent_run 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": {
    "log_agent_run": {
      "limits": [
        {
          "counter": "log_agent_run_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 log_agent_run

What does the log_agent_run tool do? +

log_agent_run. 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 log_agent_run? +

Register the Metis Public Health MCP server in PolicyLayer and add a rule for log_agent_run: 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 log_agent_run? +

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

Can I rate-limit log_agent_run? +

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

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

log_agent_run 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.