ai.ocr.extract
Extract text from any image or PDF URL using OCR — supports 20+ languages including English, Russian, Chinese, Japanese, Korean, Arabic. Returns recognized text. Handles PNG, JPG, GIF, BMP, PDF, TIFF (OCR.space)
This record as markdown: /tools/io-github-whiteknightonhorse-apibase/ai.ocr.extract.md
What ai.ocr.extract does on Apibase
AI agents call ai.ocr.extract to retrieve information from Apibase 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 |
|---|---|---|---|
url | string | Yes | URL of the image or PDF to extract text from (PNG, JPG, GIF, BMP, PDF, TIFF supported) |
filetype | string | — | File type hint — set if URL has no extension or content-type is wrong |
language | string | — | OCR language: "eng" (English, default), "rus" (Russian), "ger" (German), "fre" (French), "spa" (Spanish), "jpn" (Japanese), "kor" (Korean), "chs" (Chinese Simpl |
detect_orientation | boolean | — | Auto-detect and correct image orientation (default false) |
Parameters from the server's own tool schema.
Why ai.ocr.extract is rated Low
Tool retrieves text data from images/PDFs without modifying, deleting, or executing code.
From the tool's definition Extract text from image or PDF URL using OCR. Returns recognized text.
Risk signalsAccepts URL/endpoint input (url)
Attacks that exploit this kind of access
The rule that runs ai.ocr.extract safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Apibase, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ai.ocr.extract, this is the rule to start with:
ai.ocr.extract 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 Apibase, apply this rule, and every ai.ocr.extract call is checked against it from then on.
Questions about ai.ocr.extract
Extract text from any image or PDF URL using OCR — supports 20+ languages including English, Russian, Chinese, Japanese, Korean, Arabic. Returns recognized text. Handles PNG, JPG, GIF, BMP, PDF, TIFF (OCR.space). It is categorised as a Read tool in the Apibase MCP Server, which means it retrieves data without modifying state.
ai.ocr.extract accepts 4 parameters: url, filetype, language, detect_orientation. Required: url. The full parameter table on this page comes from the server's own tool schema.
Register the Apibase MCP server in PolicyLayer and add a rule for ai.ocr.extract: 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 Apibase. Nothing to install.
ai.ocr.extract 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 ai.ocr.extract 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 ai.ocr.extract. 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.
ai.ocr.extract is provided by the Apibase MCP server (apibase-mcp-client). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Apibase, and thousands of servers like it.
This server
Across the catalogue