advanced_search
AI agents call advanced_search to retrieve information from Pinecone Economic Books without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to be a variant of the search functionality exposed by this Pinecone server. All sibling tools are read operations that retrieve or query data without side effects. No indication of write, delete, or execution capabilities.
From the tool's definition Tool name 'advanced_search' combined with server description indicating 'semantic search through a Pinecone vector database' and sibling tools like 'search_by_author', 'search_by_book', 'search_by_subject', and 'semantic_search' establish a clear read-only…
Attacks that exploit this kind of access
advanced_search. It is categorised as a Read tool in the Pinecone Economic Books MCP Server, which means it retrieves data without modifying state.
Register the Pinecone Economic Books MCP server in PolicyLayer and add a rule for advanced_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 Pinecone Economic Books. Nothing to install.
advanced_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 advanced_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 advanced_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.
advanced_search is provided by the Pinecone Economic Books MCP server (srulyrosenblat/econ_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 →