ai.ocr

OCR + layout extraction. POST { imageUrl, instruction? }. Returns verbatim transcribed text in reading order, any detected tables as markdown, the primary language, and a handwriting flag. For reading receipts, forms, screenshots, scanned pages, and labels. JPEG/PNG/GIF/WebP.

Server Mcp @2sio/mcp
Category Read
Risk class Low
Parameters 00 required

What ai.ocr does on Mcp

AI agents call ai.ocr to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why ai.ocr needs a policy

This tool retrieves and extracts data from images without side effects. It is a pure data extraction utility analogous to read/query operations. While the server itself involves financial transactions (pay-per-call USDC on Base/Solana), the ai.ocr tool itself only performs document reading and does not trigger payments or execute code.

From the tool's definition Tool performs OCR and layout extraction on images, returning 'verbatim transcribed text in reading order', 'detected tables as markdown', language detection, and handwriting flags. No modification, deletion, or execution of external systems occurs.

Questions about ai.ocr

What does the ai.ocr tool do? +

OCR + layout extraction. POST { imageUrl, instruction? }. Returns verbatim transcribed text in reading order, any detected tables as markdown, the primary language, and a handwriting flag. For reading receipts, forms, screenshots, scanned pages, and labels. JPEG/PNG/GIF/WebP. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on ai.ocr? +

Register the MCP server in PolicyLayer and add a rule for ai.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. Nothing to install.

What risk level is ai.ocr? +

ai.ocr is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit ai.ocr? +

Yes. Add a rate_limit block to the ai.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.

How do I block ai.ocr completely? +

Set action: deny in the PolicyLayer policy for ai.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.

What MCP server provides ai.ocr? +

ai.ocr is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.