AI agents call search_groups to retrieve information from Scholar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data from a semantic search index grouped by a specified field (e.g., book). It has no side effects—it only reads existing embeddings and returns results. No data is created, modified, deleted, or executed. It follows the Read category pattern of search-type operations with minimal risk if misused.
From the tool's definition Tool performs 'semantic search grouped by a payload field' with no modification capability. The server's purpose is 'semantic retrieval over a library of ebooks' and this tool retrieves grouped search results without creating, modifying, or deleting data.
Attacks that exploit this kind of access
Semantic search grouped by a payload field (default: "book"). It is categorised as a Read tool in the Scholar MCP Server, which means it retrieves data without modifying state.
Register the Scholar MCP server in PolicyLayer and add a rule for search_groups: 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 Scholar. Nothing to install.
search_groups 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 search_groups 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 search_groups. 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.
search_groups is provided by the Scholar MCP server (unlomtrois/little-librarian). 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 →