full_text_search
AI agents call full_text_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 is a read operation that retrieves or queries data from a local Calibre library without modification, deletion, or external execution. The server is explicitly read-only. Confidence is 0.85 rather than higher only because the tool description itself is empty, requiring inference from context and naming conventions.
From the tool's definition Tool name 'full_text_search' combined with server description explicitly stating 'read-only access' and 'full-text search' capability.
Attacks that exploit this kind of access
full_text_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 full_text_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.
full_text_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 full_text_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 full_text_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.
full_text_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 →