Low Risk

search_pdf

Search for text patterns (including regex) within a PDF file and return matching pages with context snippets. Supports Python-style page ranges and early stopping for performance. Use /pattern/flags format for regex (e.g.,

How to control search_pdf ↓

What search_pdf does on PDF Agent MCP

AI agents call search_pdf to retrieve information from PDF Agent MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why search_pdf needs a policy

This tool only searches and retrieves text content from PDFs—a classic Read operation. It has no side effects, does not modify data, does not execute code, and does not perform destructive operations. The severity is low because misuse would only expose information already present in the PDF; an AI agent cannot cause damage through search queries alone.

From the tool's definition Tool name is 'search_pdf' and description states it 'search[es] for text patterns' and 'return[s] matching pages with context snippets'. These are query/retrieval operations with no modification or execution capabilities.

Documented attack patterns abuse exactly the kind of access search_pdf gives an agent:

How to control search_pdf

PolicyLayer is an MCP gateway — it sits between your AI agents and PDF Agent MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for search_pdf:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_pdf": {}
  }
}

search_pdf is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register PDF Agent MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about search_pdf

What does the search_pdf tool do? +

Search for text patterns (including regex) within a PDF file and return matching pages with context snippets. Supports Python-style page ranges and early stopping for performance. Use /pattern/flags format for regex (e.g.,. It is categorised as a Read tool in the PDF Agent MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_pdf? +

Register the PDF Agent MCP server in PolicyLayer and add a rule for search_pdf: 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 Agent MCP. Nothing to install.

What risk level is search_pdf? +

search_pdf is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit search_pdf? +

Yes. Add a rate_limit block to the search_pdf 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.

How do I block search_pdf completely? +

Set action: deny in the PolicyLayer policy for search_pdf. 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.

What MCP server provides search_pdf? +

search_pdf is provided by the PDF Agent MCP server (vlad-ds/pdf-agent-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every PDF Agent MCP tool call.

Start from PDF Agent MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

7 PDF Agent MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.