Search extracted PDF text for a literal phrase and return page-numbered snippets. Use this when you need to find mentions of a clause, person, amount, or keyword before deciding which pages to inspect more deeply. All paths must be absolute paths on the user
AI agents call search_pdf_text to retrieve information from PDF Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search query on already-extracted PDF text and returns matching results. It retrieves information without creating, modifying, deleting, or executing anything. The blast radius of misuse is minimal — an agent could search for sensitive information but cannot extract, modify, or exfiltrate data beyond what a human could already see by reading the PDF. This is a straightforward Read operation.
From the tool's definition Tool description explicitly states it 'Search extracted PDF text for a literal phrase and return page-numbered snippets' — a retrieval operation with no modification or side effects. No destructive, financial, or execution capabilities mentioned.
Documented attack patterns abuse exactly the kind of access search_pdf_text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PDF Tools, and nothing reaches the server without passing your rules. This is the rule we recommend for search_pdf_text:
{
"version": "1",
"default": "deny",
"tools": {
"search_pdf_text": {}
}
}search_pdf_text is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search extracted PDF text for a literal phrase and return page-numbered snippets. Use this when you need to find mentions of a clause, person, amount, or keyword before deciding which pages to inspect more deeply. All paths must be absolute paths on the user. It is categorised as a Read tool in the PDF Tools MCP Server, which means it retrieves data without modifying state.
Register the PDF Tools MCP server in PolicyLayer and add a rule for search_pdf_text: 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 Tools. Nothing to install.
search_pdf_text 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_pdf_text 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_pdf_text. 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_pdf_text is provided by the PDF Tools MCP server (open-document-alliance/pdf-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 36 PDF Tools tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
36 PDF Tools tools catalogued and risk-classified — across an index of 42,500+ MCP servers.