Extract text from an image URL using OCR.
AI agents call ocr to retrieve information from Mcp Services without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
OCR (Optical Character Recognition) is a data extraction utility that processes an image and returns recognized text. It has no side effects, does not modify any data, does not execute code, and does not involve financial transactions. The operation is purely informational/retrieval-based, fitting the Read category.
From the tool's definition Tool name 'ocr' and description 'Extract text from an image URL using OCR' indicate a read-only operation that retrieves text content from images without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
Extract text from an image URL using OCR. It is categorised as a Read tool in the Mcp Services MCP Server, which means it retrieves data without modifying state.
Register the Mcp Services MCP server in PolicyLayer and add a rule for 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 Services. Nothing to install.
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 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 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.
ocr is provided by the Mcp Services MCP server (san-npm/mcp-services). 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 →