treehouse_complete · Treehouse Worktree MCP: Risk & Policy

WHAT IT DOES

What treehouse_complete does on Treehouse Worktree

AI agents invoke treehouse_complete to trigger actions in Treehouse Worktree. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why treehouse_complete needs a policy

This tool finalizes work on a git worktree and can merge changes back into the target branch. Merging is an external git operation with significant side effects (modifying branch history, potentially triggering conflicts). It spans Write and Execute territory; since it triggers git merge operations and branch manipulation, Execute is the most appropriate category.

From the tool's definition 'Complete work on a worktree, optionally merging changes back'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

treehouse_complete Rate-limited

treehouse_complete stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "treehouse_complete": {
      "limits": [
        {
          "counter": "treehouse_complete_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Treehouse Worktree, so you can run agents against it safely.

FAQ

Questions about treehouse_complete

What does the treehouse_complete tool do? +

Complete work on a worktree, optionally merging changes back. It is categorised as a Execute tool in the Treehouse Worktree MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on treehouse_complete? +

Register the Treehouse Worktree MCP server in PolicyLayer and add a rule for treehouse_complete: 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 Treehouse Worktree. Nothing to install.

What risk level is treehouse_complete? +

treehouse_complete is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit treehouse_complete? +

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

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

treehouse_complete is provided by the Treehouse Worktree MCP server (mark-hingston/treehouse-worktree). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.