treehouse_prune · Treehouse Worktree MCP: Risk & Policy

WHAT IT DOES

What treehouse_prune does on Treehouse Worktree

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

WHY IT NEEDS A POLICY

Why treehouse_prune needs a policy

This tool modifies the git worktree metadata by removing orphaned entries, which is a reversible operation (entries could theoretically be recreated or recovered from git state). This is Write rather than Destructive because it targets metadata/state entries rather than core repository data or user work.

From the tool's definition Tool performs cleanup of 'orphaned worktree entries,' which modifies the state of the worktree management system by removing obsolete entries. The description indicates it 'cleans up' entries rather than querying or deleting actual code/branches.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

treehouse_prune Rate-limited

treehouse_prune 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": {
    "treehouse_prune": {
      "limits": [
        {
          "counter": "treehouse_prune_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 Treehouse Worktree, so you can run agents against it safely.

FAQ

Questions about treehouse_prune

What does the treehouse_prune tool do? +

Clean up orphaned worktree entries. It is categorised as a Write tool in the Treehouse Worktree MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on treehouse_prune? +

Register the Treehouse Worktree MCP server in PolicyLayer and add a rule for treehouse_prune: 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_prune? +

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

Can I rate-limit treehouse_prune? +

Yes. Add a rate_limit block to the treehouse_prune 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_prune completely? +

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

treehouse_prune 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.