What vision model does the server use?
It uses OpenAI’s GPT‑4.1‑mini model, optimized for text extraction from images with high‑detail analysis.
OpenAI OCR MCP Server
@cjus
Basic information
About OpenAI OCR MCP Server
OpenAPI (based) text from image extraction MCP Server
OpenAI OCR MCP Server config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryOpenAI OCR MCP Server tools
Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is OpenAI OCR MCP Server?
OpenAI OCR MCP Server is a Model Context Protocol (MCP) server that uses OpenAI’s GPT‑4.1‑mini vision model to extract text from images. It integrates with Cursor IDE, allowing users to select an image file and receive the extracted text directly in the IDE, as well as saved as a separate text file.
How to use OpenAI OCR MCP Server?
Install dependencies (npm install), build the TypeScript code (npm run build), and set the OPENAI_API_KEY environment variable in a .env file. In Cursor IDE, configure the MCP server, then use the OCR tool via the command palette to select an image file. The extracted text is displayed in Cursor and automatically saved as a text file next to the source image.
Key features of OpenAI OCR MCP Server
- Text extraction from images via OpenAI’s GPT‑4.1‑mini vision model.
- Automatic creation of text files alongside the source image.
- Content‑based file naming using a unique 8‑character hash.
- Supports JPEG, PNG, GIF, and WebP image formats.
- Robust error handling with detailed, debug‑friendly logging.
Use cases of OpenAI OCR MCP Server
- Extracting text from scanned documents or photos directly in Cursor IDE.
- Automatically saving OCR results as organized, hash‑named text files.
- Processing batches of images with consistent error reporting and file validation.
- Enabling text extraction workflows within a code editor environment.
Frequently asked questions
Which image formats are supported?
The server supports JPEG/JPG, PNG, GIF, and WebP formats.
Is there a file size limit for images?
Yes, images must be 5MB or smaller; larger files are rejected with an error message.
How is the extracted text file named?
The text file follows the pattern `{original_image_name}-{content_hash}.txt`, where the hash is an 8‑character unique identifier derived from the extracted text.
Do I need an OpenAI API key to use the server?
Yes, a valid OpenAI API key (either standard `sk-...` or project‑specific `sk-proj-...`) must be set in the `OPENAI_API_KEY` environment variable.
More AI & Agents MCP servers
GoBuy - Product Trust
gobuy-aiGoBuy gives AI agents marketplace-evidence trust scores. One call returns a 0–100 Evidence Score with observed/missing signals, freshness, and product context. Tools: • check_product_trust — inspect one Amazon, Walmart,
Quest: Hire a Human
Quest (hireahuman.quest)Hire a verified local human for small real-world tasks your AI agent can't do: errands, queues, pickups, in-person checks and on-site photos. Your agent posts a quest, local humans send offers, and your user picks one an
WordPress MCP Server
miniOrangeminiOrange WordPress MCP Server turns a WordPress site into a Model Context Protocol server, so AI clients like Claude, ChatGPT, Cursor, Gemini and Windsurf can read and edit the site through chat instead of the admin da
AskOne: Live Q&A and Polls
phurynRun free live audience Q&A and polls from your agent: start an AskOne room, add and launch a poll, approve or hide questions and mark them answered, close the room, then read the questions as a FAQ draft and get the resu
hausverbot
eliduarte37BERGHAIN MCP server — sovereign AI stress-testing mcp / ai / multi-agent / adversarial / stress-test / claude
Comments