OCR

Provides OCR capabilities via MCP with Tesseract support; accepts image files, URLs, or raw bytes.

python

28

GitHub Stars

python

Language

3 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "rjn32s-mcp-ocr": {
      "command": "python",
      "args": [
        "-m",
        "mcp_ocr"
      ]
    }
  }
}

The MCP OCR Server provides production-grade optical character recognition capabilities through a simple MCP interface. It automatically installs Tesseract where supported, accepts multiple input formats, and exposes OCR functions you can invoke from any MCP client. This makes it easy to integrate image-to-text extraction into your workflows and apps.

How to use

You run the OCR server locally as an MCP endpoint and then call its tools from your MCP client. The core capabilities are to extract text from images and to enumerate the supported OCR languages. Start by launching the server, then call the available tools from your client code.

To use the OCR service from your client, point your requests at the server that you launched locally. You can pass image data in different forms, and the server will return the extracted text. Use the available functions to request OCR results and to query which languages are supported.

How to install

Prerequisites you need before installation:

Python 3.8+ (required to run the server)
A command runner for Python package execution (see below)

Installation steps you should follow exactly as written:

pip install mcp-ocr

uv pip install mcp-ocr

Configure and run the server

After installing, start the OCR server locally so you can connect to it from an MCP client.

python -m mcp_ocr

Claude Desktop integration

If you are using Claude Desktop, configure the MCP server by adding a small config entry that points to the local server. Create or update the file at your user profile path and include the following configuration.

{
  "mcpServers": {
      "ocr": {
          "command": "python",
          "args": ["-m", "mcp_ocr"]
      }
  }
}

OCR