get_repository_tree
Get the tree structure (files and directories) of a GitHub repository at a specific ref or SHA
This record as markdown: /tools/github/get-repository-tree.md
What get_repository_tree does on GitHub
AI agents call get_repository_tree to retrieve information from GitHub without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
repo | string | — | Repository name |
owner | string | — | Repository owner (username or organization) |
tree_sha | string | — | The SHA1 value or ref (branch or tag) name of the tree. Defaults to the repository's default branch |
recursive | boolean | — | Setting this parameter to true returns the objects or subtrees referenced by the tree. Default is false |
path_filter | string | — | Optional path prefix to filter the tree results (e.g., 'src/' to only show files in the src directory) |
Parameters from the server's own tool schema.
Why get_repository_tree is rated Low
This tool queries repository structure data without creating, modifying, deleting, or executing anything. It is a straightforward data retrieval operation with minimal security impact—knowing a repository's file structure is generally non-sensitive metadata, similar to browsing a public GitHub UI. Severity is low given the read-only nature and typical public availability of repository structures.
From the tool's definition Tool description states 'Get the tree structure (files and directories)' - a retrieval operation with no modification or side effects. The name 'get_repository_tree' and verb 'Get' confirm read-only intent.
Attacks that exploit this kind of access
The rule that runs get_repository_tree safely
PolicyLayer is an MCP gateway: it sits between your AI agents and GitHub, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_repository_tree, this is the rule to start with:
get_repository_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 GitHub, apply this rule, and every get_repository_tree call is checked against it from then on.
Questions about get_repository_tree
Get the tree structure (files and directories) of a GitHub repository at a specific ref or SHA. It is categorised as a Read tool in the GitHub MCP Server, which means it retrieves data without modifying state.
get_repository_tree accepts 5 parameters: repo, owner, tree_sha, recursive, path_filter. The full parameter table on this page comes from the server's own tool schema.
Register the GitHub MCP server in PolicyLayer and add a rule for get_repository_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 GitHub. Nothing to install.
get_repository_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 get_repository_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 get_repository_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.
get_repository_tree is provided by the GitHub MCP server (oci:ghcr.io/github/github-mcp-server:1.3.0). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on GitHub, and thousands of servers like it.
This server
Across the catalogue