AI agents call prompthub_get_repo to retrieve information from Prompthub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries repository metadata and structure without creating, modifying, or deleting data. It has no side effects and poses minimal security risk, making it a straightforward Read operation.
From the tool's definition Tool name is 'prompthub_get_repo' and description states 'Fetch one repository' — fetch is a read operation. Returns README and file tree (no modifications or destructive actions).
Attacks that exploit this kind of access
Fetch one repository by owner handle and name, including its README and full file tree. Returns. It is categorised as a Read tool in the Prompthub MCP Server, which means it retrieves data without modifying state.
Register the Prompthub MCP server in PolicyLayer and add a rule for prompthub_get_repo: 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 Prompthub. Nothing to install.
prompthub_get_repo 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 prompthub_get_repo 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 prompthub_get_repo. 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.
prompthub_get_repo is provided by the Prompthub MCP server (lionelhao/prompthub-mcp). 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 →