Low Risk

tree

tree

How to control tree ↓

What tree does on PythonAnywhere MCP Server

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

Low Risk

Why tree needs a policy

The tool name 'tree' strongly suggests a read-only directory listing operation (like the Unix 'tree' command), which retrieves and displays file system hierarchy without modifying anything. The empty description lowers confidence, but in the context of a file management server, this interpretation is most plausible.

From the tool's definition Tool name 'tree' — description is empty and uninformative. Based on conventional meaning (directory tree listing) and server context (file/webapp management on PythonAnywhere), 'tree' most likely lists file/directory structure.

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

How to control tree

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

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

tree 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 PythonAnywhere MCP Server — 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 tree

What does the tree tool do? +

tree. It is categorised as a Read tool in the PythonAnywhere MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on tree? +

Register the PythonAnywhere MCP Server MCP server in PolicyLayer and add a rule for tree: 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 PythonAnywhere MCP Server. Nothing to install.

What risk level is tree? +

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

Can I rate-limit tree? +

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

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

tree is provided by the PythonAnywhere MCP Server MCP server (pythonanywhere/pythonanywhere-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every PythonAnywhere MCP Server tool call.

Start from PythonAnywhere MCP Server, 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.

20 PythonAnywhere MCP Server 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.