AI agents call prompthub_search 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 performs a read-only search operation that retrieves repository metadata from public sources. It has no side effects, cannot modify or delete data, cannot execute code, and cannot commit financial obligations. The narrow scope (public repos, summaries only) and query-based nature classify it as a Read action with low risk.
From the tool's definition Tool description states 'Search public PromptHub repositories by keyword. Returns repo summaries (no file trees).' The action is explicitly a search operation that retrieves and queries data with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Search public PromptHub repositories by keyword. Returns repo summaries (no file trees). An empty query returns no results. 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_search: 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_search 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_search 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_search. 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_search 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 →