AI agents call get_marketplace_stats to retrieve information from Hermtica without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves marketplace statistics and trend data with no side effects. It queries aggregated information (counts, breakdowns, trends) without creating, modifying, deleting, or executing any operations. The operation is purely observational and safe for autonomous agents.
From the tool's definition Tool name and description indicate data retrieval only: 'Get statistics about the Hermtica marketplace. See total services, free tools available, category breakdowns, and market trends.' These are read-only aggregated metrics with no modification, deletion,…
Attacks that exploit this kind of access
Get statistics about the Hermtica marketplace. See total services, free tools available, category breakdowns, and market trends. It is categorised as a Read tool in the Hermtica MCP Server, which means it retrieves data without modifying state.
Register the Hermtica MCP server in PolicyLayer and add a rule for get_marketplace_stats: 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 Hermtica. Nothing to install.
get_marketplace_stats 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_marketplace_stats 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_marketplace_stats. 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_marketplace_stats is provided by the Hermtica MCP server (realmnohgee/hermtica). 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 →