unified_search
AI agents call unified_search to retrieve information from Neolibrarian MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs search operations on a read-only Calibre library. Despite the empty description, the server's explicit read-only constraint, the nature of sibling tools, and the naming pattern ('unified_search' suggests a search/query function) all point to a Read category tool. No modifications, deletions, code execution, or financial operations are possible.
From the tool's definition Tool is part of a server explicitly described as 'read-only access to local Calibre libraries' with operations like 'searching metadata', 'inspecting book formats', and 'extracting content samples'.
Attacks that exploit this kind of access
unified_search. It is categorised as a Read tool in the Neolibrarian MCP MCP Server, which means it retrieves data without modifying state.
Register the Neolibrarian MCP server in PolicyLayer and add a rule for unified_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 Neolibrarian MCP. Nothing to install.
unified_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 unified_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 unified_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.
unified_search is provided by the Neolibrarian MCP server (pshap/mcp-neolibrarian). 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 →