Low Risk

worktree_list

List all git worktrees in the workspace

How to control worktree_list ↓

What worktree_list does on Climux

AI agents call worktree_list to retrieve information from Climux without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why worktree_list needs a policy

This tool retrieves and lists existing git worktrees, which is a read-only operation that queries the workspace state without modifying, deleting, or executing any code. It has minimal blast radius if misused by an AI agent, as it only provides informational data about the workspace structure.

From the tool's definition Tool name is 'worktree_list' and description states 'List all git worktrees in the workspace' — a query operation with no side effects.

Documented attack patterns abuse exactly the kind of access worktree_list gives an agent:

How to control worktree_list

PolicyLayer is an MCP gateway — it sits between your AI agents and Climux, and nothing reaches the server without passing your rules. This is the rule we recommend for worktree_list:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "worktree_list": {}
  }
}

worktree_list is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Climux — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about worktree_list

What does the worktree_list tool do? +

List all git worktrees in the workspace. It is categorised as a Read tool in the Climux MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on worktree_list? +

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

What risk level is worktree_list? +

worktree_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit worktree_list? +

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

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

worktree_list is provided by the Climux MCP server (veithly/climux). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Climux tool call.

Start from Climux, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

9 Climux tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.