Search a specific library source by name. Use library_ask instead for natural language queries across multiple sources. Sources marked [full text] support library_read and library_ingest. Sources marked [metadata] return discovery info and external URLs only. Returns: Array of { id, source, title...
AI agents call library_search to retrieve information from Alexandria MCP 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 public library data without side effects. It returns structured metadata about academic papers, books, and legal records from public digital libraries. No data is created, modified, deleted, or executed. The mention of [metadata] vs [full text] sources clarifies that this search function itself only returns discovery information, not full content manipulation.
From the tool's definition Tool description explicitly states it 'Search a specific library source' and 'Returns: Array of { id, source, title, authors, year, language, subjects, hasFullText, previewUrl, description }'.
Attacks that exploit this kind of access
Search a specific library source by name. Use library_ask instead for natural language queries across multiple sources. Sources marked [full text] support library_read and library_ingest. Sources marked [metadata] return discovery info and external URLs only. Returns: Array of { id, source, title, authors, year, language, subjects, hasFullText, previewUrl, description }. It is categorised as a Read tool in the Alexandria MCP MCP Server, which means it retrieves data without modifying state.
Register the Alexandria MCP server in PolicyLayer and add a rule for library_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 Alexandria MCP. Nothing to install.
library_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 library_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 library_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.
library_search is provided by the Alexandria MCP server (the-40-thieves/alexandria-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 →