Fetch the current state + results for a search by its search_id. Use this to recover a search that timed out client-side, or to re-read a recent one. Free.
AI agents call get_search to retrieve information from Gorilla MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a retrieval operation that queries previously-created search results. It has no side effects, cannot modify data, and poses minimal risk. The 'Fetch' verb and read-only nature confirm Read category. The tool operates on search_ids that already exist, making it a safe lookup operation typical of low-severity read access.
From the tool's definition Fetch the current state + results for a search by its search_id. The tool retrieves data (search results) without modifying, creating, or deleting anything.
Attacks that exploit this kind of access
Fetch the current state + results for a search by its search_id. Use this to recover a search that timed out client-side, or to re-read a recent one. Free. It is categorised as a Read tool in the Gorilla MCP MCP Server, which means it retrieves data without modifying state.
Register the Gorilla MCP server in PolicyLayer and add a rule for get_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 Gorilla MCP. Nothing to install.
get_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 get_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 get_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.
get_search is provided by the Gorilla MCP server (opusforge/gorilla-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 →