递归显示 GitHub 仓库的完整目录树结构。当需要了解仓库的整体文件组织时使用此工具，它提供比 github_ls 更全面的视图。
AI agents call github_tree to retrieve information from MCP Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves structural metadata (directory tree) from a GitHub repository. It performs a read-only operation analogous to 'ls -R' or 'find', returning information about files and folders without creating, modifying, executing, or deleting anything. No side effects or external operations are triggered beyond fetching publicly available repository structure data.
From the tool's definition Tool description indicates it "recursively displays the complete directory tree structure" of a GitHub repository, providing "a more comprehensive view" than listing.
Attacks that exploit this kind of access
递归显示 GitHub 仓库的完整目录树结构。当需要了解仓库的整体文件组织时使用此工具，它提供比 github_ls 更全面的视图。. It is categorised as a Read tool in the MCP Toolkit MCP Server, which means it retrieves data without modifying state.
Register the MCP Toolkit MCP server in PolicyLayer and add a rule for github_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 MCP Toolkit. Nothing to install.
github_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 github_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 github_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.
github_tree is provided by the MCP Toolkit MCP server (zxfgds/mcp-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →