log_action · AgentOS MCP: Risk & Policy

WHAT IT DOES

What log_action does on AgentOS

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

WHY IT NEEDS A POLICY

Why log_action needs a policy

The tool writes a new log entry to an audit/debug log. This is a reversible write operation (appending data) with no destructive, financial, or execution side effects. Severity is low because log entries are informational records that pose minimal risk even if misused.

From the tool's definition Append a structured log entry for debugging and audit trail

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

log_action Rate-limited

log_action 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_action": {
      "limits": [
        {
          "counter": "log_action_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 AgentOS, so you can run agents against it safely.

FAQ

Questions about log_action

What does the log_action tool do? +

Append a structured log entry for debugging and audit trail. It is categorised as a Write tool in the AgentOS 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_action? +

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

What risk level is log_action? +

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

Can I rate-limit log_action? +

Yes. Add a rate_limit block to the log_action 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_action completely? +

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

log_action is provided by the AgentOS MCP server (netflypsb/agentos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.