directory_tree
Get a recursive tree view of files and directories as a JSON structure.
This record as markdown: /tools/cowork-bench/directory-tree.md
What directory_tree does on Cowork Bench
AI agents call directory_tree to retrieve information from Cowork Bench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why directory_tree is rated Low
This tool retrieves and displays directory/file information in a read-only manner. There are no side effects, data modification, deletion, code execution, or financial implications. The only potential risk is information disclosure if sensitive file structures exist, but the severity remains low as it is purely informational.
From the tool's definition Tool description states it 'Get[s] a recursive tree view of files and directories as a JSON structure' — a query operation with no modification capability.
Attacks that exploit this kind of access
The rule that runs directory_tree safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cowork Bench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For directory_tree, this is the rule to start with:
directory_tree is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Cowork Bench, apply this rule, and every directory_tree call is checked against it from then on.
Questions about directory_tree
Get a recursive tree view of files and directories as a JSON structure. It is categorised as a Read tool in the Cowork Bench MCP Server, which means it retrieves data without modifying state.
Register the Cowork Bench MCP server in PolicyLayer and add a rule for directory_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 Cowork Bench. Nothing to install.
directory_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 directory_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 directory_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.
directory_tree is provided by the Cowork Bench MCP server (0717376/cowork_bench). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cowork Bench, and thousands of servers like it.
This server
Across the catalogue