AI agents call get_entire_repo_contents to retrieve information from MCP GitHub Reader without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves repository contents without side effects. While severity is medium (not low) due to potential exposure of sensitive data like credentials, API keys, or proprietary code that might be accidentally committed, it remains a Read operation. Confidence is slightly reduced because the description is empty, requiring inference from context and naming.
From the tool's definition Tool name 'get_entire_repo_contents' indicates retrieval of repository data without modification. Server description emphasizes 'file access' and 'repository analysis' as read-only operations.
Documented attack patterns abuse exactly the kind of access get_entire_repo_contents gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP GitHub Reader, and nothing reaches the server without passing your rules. This is the rule we recommend for get_entire_repo_contents:
{
"version": "1",
"default": "deny",
"tools": {
"get_entire_repo_contents": {}
}
}get_entire_repo_contents 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.
get_entire_repo_contents. It is categorised as a Read tool in the MCP GitHub Reader MCP Server, which means it retrieves data without modifying state.
Register the MCP GitHub Reader MCP server in PolicyLayer and add a rule for get_entire_repo_contents: 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 GitHub Reader. Nothing to install.
get_entire_repo_contents 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_entire_repo_contents 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_entire_repo_contents. 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_entire_repo_contents is provided by the MCP GitHub Reader MCP server (skydeckai/mcp-github-reader-prod). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP GitHub Reader, 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.
4 MCP GitHub Reader tools catalogued and risk-classified — across an index of 43,000+ MCP servers.