AI agents call perform_pdf_ocr to retrieve information from MCP OCR Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
OCR extraction of text from PDF documents is a read-only operation that retrieves data without modifying or deleting content. It has no side effects on the source document and represents a standard query/retrieval capability. The low severity reflects minimal blast radius if misused—an AI agent cannot damage systems or access beyond what is already visible in provided PDFs.
From the tool's definition Tool name 'perform_pdf_ocr' and server description indicates OCR extraction from images/PDFs. The server provides 'Extracts text from images' with 'no side effects' pattern (similar Read tools listed: get_supported_languages, image_to_data, perform_batch_ocr,…
Documented attack patterns abuse exactly the kind of access perform_pdf_ocr gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP OCR Server, and nothing reaches the server without passing your rules. This is the rule we recommend for perform_pdf_ocr:
{
"version": "1",
"default": "deny",
"tools": {
"perform_pdf_ocr": {}
}
}perform_pdf_ocr is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
perform_pdf_ocr. It is categorised as a Read tool in the MCP OCR Server MCP Server, which means it retrieves data without modifying state.
Register the MCP OCR Server MCP server in PolicyLayer and add a rule for perform_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 MCP OCR Server. Nothing to install.
perform_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 perform_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 perform_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.
perform_pdf_ocr is provided by the MCP OCR Server MCP server (rjn32s/mcp-ocr). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 MCP OCR Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 MCP OCR Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.