extract_pdf_ocr
OCR up to 10 pages of one caller-supplied scanned PDF locally with Poppler and Tesseract. Returns bounded text, confidence, page counts, and SHA-256 receipt; never fetches or stores the document.
This record as markdown: /tools/io-github-davidmosiah-delx-mcp-server/extract-pdf-ocr.md
What extract_pdf_ocr does on Delx MCP Server
AI agents call extract_pdf_ocr to retrieve information from Delx MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
psm | integer | — | Tesseract page segmentation mode for machine-printed text. |
max_chars | integer | — | |
max_pages | integer | — | |
pdf_base64 | string | Yes | One base64-encoded PDF up to 4 MiB decoded; application/pdf data URIs are accepted. |
file_base64 | string | — | Alias for pdf_base64. |
Parameters from the server's own tool schema.
Why extract_pdf_ocr is rated Low
The tool performs optical character recognition on a caller-supplied PDF document and returns extracted text data. This is a data retrieval operation with no side effects—it reads content without modifying, deleting, or executing anything. The explicit note that it 'never fetches or stores the document' confirms no persistent state changes.
From the tool's definition Tool description states it 'extract[s]' text from PDFs using OCR, 'Returns bounded text, confidence, page counts, and SHA-256 receipt; never fetches or stores the document.' No modification, deletion, code execution, or financial operations occur.
Attacks that exploit this kind of access
The rule that runs extract_pdf_ocr safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Delx MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For extract_pdf_ocr, this is the rule to start with:
extract_pdf_ocr is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Delx MCP Server, apply this rule, and every extract_pdf_ocr call is checked against it from then on.
Questions about extract_pdf_ocr
OCR up to 10 pages of one caller-supplied scanned PDF locally with Poppler and Tesseract. Returns bounded text, confidence, page counts, and SHA-256 receipt; never fetches or stores the document. It is categorised as a Read tool in the Delx MCP Server MCP Server, which means it retrieves data without modifying state.
extract_pdf_ocr accepts 5 parameters: psm, max_chars, max_pages, pdf_base64, file_base64. Required: pdf_base64. The full parameter table on this page comes from the server's own tool schema.
Register the Delx MCP Server MCP server in PolicyLayer and add a rule for extract_pdf_ocr: 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 Delx MCP Server. Nothing to install.
extract_pdf_ocr 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 extract_pdf_ocr 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 extract_pdf_ocr. 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.
extract_pdf_ocr is provided by the Delx MCP Server MCP server (delx-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Delx MCP Server, and thousands of servers like it.
This server
Across the catalogue