end_starlog · Starlog MCP: Risk & Policy

WHAT IT DOES

What end_starlog does on Starlog

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

WHY IT NEEDS A POLICY

Why end_starlog needs a policy

This tool finalizes/closes a work session and writes a summary of outcomes. It creates or modifies session tracking data. There's no indication it deletes anything irreversibly or executes code; it's a write operation that records session completion state.

From the tool's definition Complete session with summary and outcomes. Use this to properly close your work session with a summary of what was accomplished.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

end_starlog Rate-limited

end_starlog 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": {
    "end_starlog": {
      "limits": [
        {
          "counter": "end_starlog_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 Starlog, so you can run agents against it safely.

FAQ

Questions about end_starlog

What does the end_starlog tool do? +

Complete session with summary and outcomes. Use this to properly close your work session with a summary of what was accomplished. It is categorised as a Write tool in the Starlog MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on end_starlog? +

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

What risk level is end_starlog? +

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

Can I rate-limit end_starlog? +

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

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

end_starlog is provided by the Starlog MCP server (sancovp/starlog-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.