AI agents call marketplace_search to retrieve information from Loreto without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
marketplace_search retrieves or queries marketplace listings without modifying, deleting, or executing operations. It fits the Read category: retrieves data with no side effects. Severity is low because marketplace search operations have minimal blast radius—they only expose metadata about publicly available skills and cannot affect user data, finances, or system integrity.
From the tool's definition Tool name 'marketplace_search' indicates a search operation. The server context describes a skills marketplace where users browse and discover existing skills.
Documented attack patterns abuse exactly the kind of access marketplace_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Loreto, and nothing reaches the server without passing your rules. This is the rule we recommend for marketplace_search:
{
"version": "1",
"default": "deny",
"tools": {
"marketplace_search": {}
}
}marketplace_search 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.
marketplace_search. It is categorised as a Read tool in the Loreto MCP Server, which means it retrieves data without modifying state.
Register the Loreto MCP server in PolicyLayer and add a rule for marketplace_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 Loreto. Nothing to install.
marketplace_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 marketplace_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 marketplace_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.
marketplace_search is provided by the Loreto MCP server (kopias/loreto-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Loreto, 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.
13 Loreto tools catalogued and risk-classified — across an index of 43,000+ MCP servers.