// SCAN REPORT

Treehouse Worktree

13 tools. 10 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 29 Jun 2026

10 can modify or destroy data

3 read-only

13 tools total

Community server · catalogue entry verified 29/06/2026

How to control Treehouse Worktree ↓

TOOL MAP

What Treehouse Worktree exposes to your agents

Read (3) Write / Execute (8) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Treehouse Worktree tools

Destructive · High treehouse_clean This tool irreversibly deletes git worktrees based on a retention policy. Destructive · High treehouse_remove Removing a worktree irreversibly deletes local workspace state and files. Execute · High treehouse_complete This tool finalizes work on a git worktree and can merge changes back into the target branch. Execute · High treehouse_resolve Resolving merge conflicts by applying a strategy actively modifies file contents and git state in a way that could overwrite changes depending on the chosen strategy (e.g., 'ours' or 'theirs').

10 of Treehouse Worktree's 13 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Treehouse Worktree

PolicyLayer is an MCP gateway — it sits between your AI agents and Treehouse Worktree, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "treehouse_clean": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "treehouse_abort": {
    "limits": [
      {
        "counter": "treehouse_abort_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "treehouse_conflicts": {
    "limits": [
      {
        "counter": "treehouse_conflicts_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Treehouse Worktree — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON TREEHOUSE WORKTREE →

Instant setup, no code required.

FULL CATALOGUE

All 13 Treehouse Worktree tools

DESTRUCTIVE 2 tools

Destructive treehouse_clean Remove old worktrees based on retention policy Destructive treehouse_remove Remove a worktree

EXECUTE 2 tools

Execute treehouse_complete Complete work on a worktree, optionally merging changes back Execute treehouse_resolve Resolve merge conflicts using a specific strategy

WRITE 6 tools

Write treehouse_abort Abort a merge operation in progress Write treehouse_create Create a new worktree for parallel development. Optionally lock it for an agent. Write treehouse_init Initialize treehouse configuration in the current repository Write treehouse_lock Lock a worktree to prevent other agents from using it Write treehouse_prune Clean up orphaned worktree entries Write treehouse_unlock Unlock a worktree to allow other agents to use it

READ 3 tools

Read treehouse_conflicts Check for merge conflicts in a worktree or the main repository Read treehouse_list List all git worktrees with their status and lock information Read treehouse_status Get detailed status of a specific worktree or all worktrees

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Treehouse Worktree

Can an AI agent delete data through the Treehouse Worktree MCP server? +

Yes. The Treehouse Worktree server exposes 2 destructive tools including treehouse_clean, treehouse_remove. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Treehouse Worktree? +

The Treehouse Worktree server has 6 write tools including treehouse_abort, treehouse_create, treehouse_init. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Treehouse Worktree.

How many tools does the Treehouse Worktree MCP server expose? +

13 tools across 3 categories: Destructive, Read, Write. 3 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Treehouse Worktree? +

Register the Treehouse Worktree MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Treehouse Worktree tool call.

Deterministic rules across all 13 Treehouse Worktree tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TREEHOUSE WORKTREE →

Instant setup, no code required.

13 Treehouse Worktree tools catalogued and risk-classified — across an index of 43,000+ MCP servers.