List files and directories in a GitHub repository path
AI agents call github_list_files to retrieve information from MCP Server App without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves repository structure information from GitHub without creating, modifying, deleting, or executing anything. It is a straightforward read operation analogous to 'list' or 'get'. The blast radius of misuse is minimal since an AI agent can only discover what files exist in a repository, which is typically already public information.
From the tool's definition Tool name is 'github_list_files' and description states it 'List files and directories in a GitHub repository path' — a pure query/retrieval operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
List files and directories in a GitHub repository path. It is categorised as a Read tool in the MCP Server App MCP Server, which means it retrieves data without modifying state.
Register the MCP Server App MCP server in PolicyLayer and add a rule for github_list_files: 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 Server App. Nothing to install.
github_list_files 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_list_files 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_list_files. 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_list_files is provided by the MCP Server App MCP server (ovokpus/mcp-server-app). 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 →