Advertise
MCP.so
Sign In
G

Gemini OCR MCP Server

@WindoC

Repository

Basic information

Category

AI & Agents

Transports

stdio

Author

WindoC

Submitted by

Antonio Cheong

About Gemini OCR MCP Server

This project provides a simple yet powerful OCR (Optical Character Recognition) service through a FastMCP server, leveraging the capabilities of the Google Gemini API. It allows you to extract text from images either by providing a file path or a base64 encoded string.

#ocr#gemini

Gemini OCR MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "gemini-ocr-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/your/project/gemini-ocr-mcp",
        "run",
        "gemini-ocr-mcp.py"
      ],
      "env": {
        "GEMINI_MODEL": "gemini-2.5-flash-preview-05-20",
        "GEMINI_API_KEY": "YOUR_GEMINI_API_KEY"
      }
    }
  }
}

Gemini 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 Gemini OCR MCP?

Gemini OCR MCP is an MCP server that provides Optical Character Recognition (OCR) by leveraging the Google Gemini API. It allows you to extract text from images either by providing a file path or a base64-encoded string, making it useful for developers who need programmatic text extraction from images.

How to use Gemini OCR MCP?

Clone the repository, install dependencies with uv sync, and configure the server in your MCP client’s config.json using the provided Windows/macOS/Linux examples. Set the environment variables GEMINI_API_KEY and optionally GEMINI_MODEL, then invoke the tools ocr_image_file (with an image file path) or ocr_image_base64 (with a base64 image string).

Key features of Gemini OCR MCP

  • File-based OCR from local images
  • Base64 OCR from encoded image strings
  • Powered by Google Gemini models for high accuracy
  • Simple tool-based interface via FastMCP

Use cases of Gemini OCR MCP

  • Extracting text from CAPTCHA images
  • Digitizing text from scanned documents or photos
  • Processing images received as base64 data in APIs

Frequently asked questions

1

What are the prerequisites for running Gemini OCR MCP?

You need Python 3.8 or higher and a valid Google Gemini API Key from Google AI Studio.

2

How do I configure Gemini OCR MCP for my MCP client?

Add a configuration entry to your MCP client’s `config.json` specifying the command `uv`, the project directory, and environment variables `GEMINI_API_KEY` and `GEMINI_MODEL` (optional). Example configurations for Windows and Linux/macOS are provided in the README.

3

Which Gemini model does Gemini OCR MCP use?

The default model is `gemini-2.5-flash-preview-05-20`, but you can override it by setting the `GEMINI_MODEL` environment variable.

4

What tools does Gemini OCR MCP provide?

It provides two tools: `ocr_image_file` (accepts an image file path) and `ocr_image_base64` (accepts a base64-encoded image string). Both return the extracted text.

5

How does Gemini OCR MCP handle authentication?

It reads the Google Gemini API key from the `GEMINI_API_KEY` environment variable. No other authentication or transport configuration is required beyond standard MCP setup.

Comments

More AI & Agents MCP servers

hausverbot

eliduarte37

BERGHAIN MCP server — sovereign AI stress-testing mcp / ai / multi-agent / adversarial / stress-test / claude

Gemina

Gemina Tech Ltd.

Extract, search and tag any document — invoices, receipts, contracts, forms, or your own templates. 13 tools, one sign-in (OAuth 2.1) or API key, free FileTag tier, data residency in the EU, US, Israel or Asia.

早

早起鸟儿喊真人验真

shenshaoyin

早起鸟儿喊真人验真 is a remote MCP server available at http://121.40.18.232.

Poker Bots All Stars

Agent Disco

Live Texas Hold'em for AI agents: your assistant plays your 3D star, talks trash, anyone can watch.

scvd.store

seancrecord

scvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain

2
Advertise