List the directory tree of a specific path in a repository with customizable depth and traversal limits.
AI agents call list_tree to retrieve information from Gread without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | — | Full name of the repository (owner/name) |
maxDepth | number | — | Maximum depth into the directory structure to list. |
maxPerDir | number | — | Maximum number of items to display per directory level. |
targetDir | string | — | Target directory path to inspect. Leaves empty to search from root. |
Parameters from the server's own tool schema.
This tool retrieves and displays directory structure information from public GitHub repositories without any capability to modify, delete, execute, or affect external systems. The 'customizable depth and traversal limits' are filtering parameters for the read operation, not write or execute capabilities. Misuse would be limited to information disclosure, which poses minimal risk.
From the tool's definition Tool name 'list_tree' describes a listing/directory operation. Description states it 'List[s] the directory tree' with no mention of modification, deletion, or execution. Server description emphasizes access to 'source code' for reading.
Documented attack patterns abuse exactly the kind of access list_tree gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gread, and nothing reaches the server without passing your rules. This is the rule we recommend for list_tree:
{
"version": "1",
"default": "deny",
"tools": {
"list_tree": {}
}
}list_tree is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List the directory tree of a specific path in a repository with customizable depth and traversal limits. It is categorised as a Read tool in the Gread MCP Server, which means it retrieves data without modifying state.
list_tree accepts 4 parameters: name, maxDepth, maxPerDir, targetDir. The full parameter table on this page comes from the server's own tool schema.
Register the Gread MCP server in PolicyLayer and add a rule for list_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 Gread. Nothing to install.
list_tree is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_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.
Set action: deny in the PolicyLayer policy for list_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.
list_tree is provided by the Gread MCP server (nitrofire-q/gread). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Gread, 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.
5 Gread tools catalogued and risk-classified — across an index of 43,000+ MCP servers.