Low Risk

extract_text

extract_text

How to control extract_text ↓

What extract_text does on MCP PDF Forms

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

Low Risk

Why extract_text needs a policy

Despite the empty description, the tool name 'extract_text' and the exclusively read-only nature of all sibling tools on this server indicate this tool retrieves or queries text content from PDFs with no side effects. No evidence suggests it modifies, executes commands, deletes, or involves financial operations.

From the tool's definition Tool name 'extract_text' combined with sibling tools that perform read-only operations (extract_form_fields, highlight_form_field, list_pdfs, render_pdf_page, search_text). The naming convention and context strongly suggest data retrieval without modification.

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

How to control extract_text

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

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

extract_text 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 MCP PDF Forms — 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 extract_text

What does the extract_text tool do? +

extract_text. It is categorised as a Read tool in the MCP PDF Forms MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on extract_text? +

Register the MCP PDF Forms MCP server in PolicyLayer and add a rule for extract_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 MCP PDF Forms. Nothing to install.

What risk level is extract_text? +

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

Can I rate-limit extract_text? +

Yes. Add a rate_limit block to the extract_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.

How do I block extract_text completely? +

Set action: deny in the PolicyLayer policy for extract_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.

What MCP server provides extract_text? +

extract_text is provided by the MCP PDF Forms MCP server (wildebeest/mcp_pdf_forms). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP PDF Forms tool call.

Start from MCP PDF Forms, 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.

6 MCP PDF Forms 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.