ask_library
AI agents call ask_library to retrieve information from Metis Public Health without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs information retrieval from a local PDF library without modifying, executing, or deleting data. Despite the empty description, the context (server purpose as a 'research companion' that 'answers from' indexed documents) and naming convention align with Read operations. Confidence is moderate-to-high because the description is missing, but the function is sufficiently clear from context.
From the tool's definition Tool name 'ask_library' indicates querying an indexed PDF library. The server description states it 'answers from the user's own indexed PDF library with page-level citations' and 'keeps all data on the user's machine.' This is a retrieval/query operation…
Attacks that exploit this kind of access
ask_library. It is categorised as a Read tool in the Metis Public Health MCP Server, which means it retrieves data without modifying state.
Register the Metis Public Health MCP server in PolicyLayer and add a rule for ask_library: 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 Metis Public Health. Nothing to install.
ask_library 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 ask_library 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 ask_library. 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.
ask_library is provided by the Metis Public Health MCP server (sveritg/metis_ph). 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 →