Parse a PDF document and extract text, tables, and metadata from each page
AI agents call parse_pdf_document to retrieve information from docxtpl MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and extracts content (text, tables, metadata) from an existing PDF file. It has no side effects, does not modify any data, and cannot be used to cause harm beyond accessing file contents. Severity is low as it is a purely read operation on local documents.
From the tool's definition Parse a PDF document and extract text, tables, and metadata from each page
Attacks that exploit this kind of access
Parse a PDF document and extract text, tables, and metadata from each page. It is categorised as a Read tool in the docxtpl MCP Server MCP Server, which means it retrieves data without modifying state.
Register the docxtpl MCP Server MCP server in PolicyLayer and add a rule for parse_pdf_document: 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 docxtpl MCP Server. Nothing to install.
parse_pdf_document 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 parse_pdf_document 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 parse_pdf_document. 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.
parse_pdf_document is provided by the docxtpl MCP Server MCP server (z1w2r3/doc-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 →