read_by_ocr
AI agents call read_by_ocr to retrieve information from MCP PDF Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
OCR reading is a retrieval operation with no side effects. It does not modify, delete, or execute arbitrary code—it only extracts and returns text from scanned PDF content. This is a read-only operation with minimal security risk, suitable for low severity.
From the tool's definition Tool name 'read_by_ocr' indicates optical character recognition on documents; server description states it 'performing OCR on scanned documents' and 'extracting text...from PDF files'; tool description is empty but context makes function clear
Attacks that exploit this kind of access
read_by_ocr. It is categorised as a Read tool in the MCP PDF Server MCP Server, which means it retrieves data without modifying state.
Register the MCP PDF Server MCP server in PolicyLayer and add a rule for read_by_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 PDF Server. Nothing to install.
read_by_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 read_by_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 read_by_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.
read_by_ocr is provided by the MCP PDF Server MCP server (optltd/mcp-pdf-reader). 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 →