treehouse_unlock · Treehouse Worktree MCP: Risk & Policy

WHAT IT DOES

What treehouse_unlock does on Treehouse Worktree

AI agents use treehouse_unlock 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_unlock needs a policy

This tool modifies the lock state of a git worktree, which is a reversible state change (the worktree can be locked again). While it enables access by other agents rather than directly modifying code or data, it alters system state and could allow concurrent access that introduces conflicts or coordination failures.

From the tool's definition Tool name 'treehouse_unlock' and description 'Unlock a worktree to allow other agents to use it' indicate modification of worktree lock state, a reversible state change.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

treehouse_unlock Rate-limited

treehouse_unlock 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_unlock": {
      "limits": [
        {
          "counter": "treehouse_unlock_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_unlock

What does the treehouse_unlock tool do? +

Unlock a worktree to allow other agents to use it. 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_unlock? +

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

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

Can I rate-limit treehouse_unlock? +

Yes. Add a rate_limit block to the treehouse_unlock 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_unlock completely? +

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

treehouse_unlock 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.