search
AI agents call search to retrieve information from Pdf Search 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 PDF documents without modification or deletion. It returns search results, snippets, and ranked matches—classic read operations. No side effects, reversibility concerns, or resource modifications. Low severity because search results are informational with minimal blast radius if misused (e.g., information disclosure risk is low in typical PDF search contexts).
From the tool's definition Tool named 'search' on a PDF search server with 'full-text search across PDF document collections' and 'ranked results, snippets' in the server description. Sibling tools include 'read_page' and 'read_page_image', all retrieval operations.
Attacks that exploit this kind of access
search. It is categorised as a Read tool in the Pdf Search MCP Server, which means it retrieves data without modifying state.
Register the Pdf Search MCP server in PolicyLayer and add a rule for 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 Pdf Search. Nothing to install.
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 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 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.
search is provided by the Pdf Search MCP server (renvk/pdf-search-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 →