Extract text content from a PDF document with Y-coordinate-based reading order preservation. Text is extracted page by page, sorted by vertical position (top to bottom) then horizontal position (left to right), providing natural reading order. For untagged multi-column PDFs (e.g. older 新旧対照表 PDFs...
AI agents call read_text to retrieve information from Pdf Reader without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and parses text data from PDF files without modifying, deleting, or executing external operations. It is a passive data extraction utility that returns content in a structured reading order. No creation, modification, deletion, or code execution occurs. The blast radius of misuse is minimal—an AI agent could only read PDF contents it has access to, which is a standard read operation.
From the tool's definition Tool description states 'Extract text content from a PDF document' with 'reading order preservation' and 'page by page' extraction. The verbs are 'extract' and 'read', which are retrieval operations with no side effects.
Attacks that exploit this kind of access
Extract text content from a PDF document with Y-coordinate-based reading order preservation. Text is extracted page by page, sorted by vertical position (top to bottom) then horizontal position (left to right), providing natural reading order. For untagged multi-column PDFs (e.g. older 新旧対照表 PDFs that lack a structure tree), pass \. It is categorised as a Read tool in the Pdf Reader MCP Server, which means it retrieves data without modifying state.
Register the Pdf Reader MCP server in PolicyLayer and add a rule for read_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 Reader. Nothing to install.
read_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 read_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 read_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.
read_text is provided by the Pdf Reader MCP server (shuji-bonji/pdf-reader-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 →