extract_image_text
Extract English machine-printed text from one caller-supplied PNG, JPEG, or WebP locally with Tesseract. Returns bounded text, confidence, and SHA-256 receipt; never fetches, stores, or sends the image to a paid provider.
This record as markdown: /tools/io-github-davidmosiah-delx-mcp-server/extract-image-text.md
What extract_image_text does on Delx MCP Server
AI agents call extract_image_text to retrieve information from Delx MCP Server 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 |
|---|---|---|---|
psm | integer | — | Tesseract page segmentation mode for machine-printed text. |
image | string | — | Alias for image_base64. |
max_chars | integer | — | |
image_base64 | string | Yes | One base64-encoded PNG, JPEG, or WebP image up to 6 MiB decoded; image/* data URIs are accepted. |
Parameters from the server's own tool schema.
Why extract_image_text is rated Low
This is a pure data retrieval operation. It reads text from images using Tesseract OCR and returns the extracted information. There is no creation, modification, deletion, code execution, or financial transaction involved. The tool operates locally on caller-supplied input and returns structured output without altering any persistent state.
From the tool's definition The tool 'extract_image_text' performs optical character recognition (OCR) on locally-supplied images. The description explicitly states it 'Extract[s] English machine-printed text' and 'Returns bounded text, confidence, and SHA-256 receipt' with no…
Attacks that exploit this kind of access
The rule that runs extract_image_text safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Delx MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For extract_image_text, this is the rule to start with:
extract_image_text 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 Delx MCP Server, apply this rule, and every extract_image_text call is checked against it from then on.
Questions about extract_image_text
Extract English machine-printed text from one caller-supplied PNG, JPEG, or WebP locally with Tesseract. Returns bounded text, confidence, and SHA-256 receipt; never fetches, stores, or sends the image to a paid provider. It is categorised as a Read tool in the Delx MCP Server MCP Server, which means it retrieves data without modifying state.
extract_image_text accepts 4 parameters: psm, image, max_chars, image_base64. Required: image_base64. The full parameter table on this page comes from the server's own tool schema.
Register the Delx MCP Server MCP server in PolicyLayer and add a rule for extract_image_text: 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 Delx MCP Server. Nothing to install.
extract_image_text 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 extract_image_text 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 extract_image_text. 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.
extract_image_text is provided by the Delx MCP Server MCP server (delx-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Delx MCP Server, and thousands of servers like it.
This server
Across the catalogue