Handwriting OCR MCP server

The Handwriting OCR MCP Server provides integration between Model Context Protocol clients and the Handwriting OCR service. It enables you to upload documents, check their processing status, and retrieve OCR results as Markdown, making handwritten text easily accessible to AI assistants.

Prerequisites

Before getting started, make sure you have:

• Node.js installed (version 18.x or higher recommended)
• An active account on the Handwriting OCR Platform
• A valid API token from the platform

Installation

Installing via Smithery

The simplest way to install the Handwriting OCR MCP Server is through Smithery:

npx -y @smithery/cli install @Handwriting-OCR/handwriting-ocr-mcp-server --client claude

Manual Installation for Claude Desktop

To manually set up the Handwriting OCR MCP Server for Claude Desktop:

1. Update your Claude Desktop configuration file to include the MCP server
2. Add your API token as an environment variable

Example configuration:

{
    "mcpServers": {
        "handwriting-ocr": {
            "command": "node",
            "args": [
                "/path/to/handwriting-ocr/build/index.js"
            ],
            "env": {
                "API_TOKEN": "your-api-token"
            },
            "disabled": false,
            "autoApprove": []
        }
    }
}

Make sure to replace /path/to/handwriting-ocr/build/index.js with the actual path where you've stored the server files, and your-api-token with your actual API token.

Usage

The Handwriting OCR MCP Server provides three main tools:

Upload Document

Upload images or PDF documents to be processed by the OCR service. The server will handle sending the document to the Handwriting OCR API and return a job ID that you can use to check status and retrieve results.

Check Status

Check the processing status of a previously uploaded document using the job ID. This allows you to monitor when your document has completed OCR processing.

Get Text

Once processing is complete, retrieve the OCR results as Markdown text. This converts handwritten content to machine-readable text that can be used by AI assistants.

Configuration

The server requires the following environment variable:

• API_TOKEN: Your Handwriting OCR API token

You can find this token in the API settings dashboard on the Handwriting OCR Platform.

For more detailed information and advanced usage, please refer to the Handwriting OCR API Documentation.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.