home / mcp / handwriting ocr mcp server

Handwriting OCR MCP Server

Provides an MCP server to upload images/PDFs, check status, and return OCR results as Markdown.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "handwriting-ocr-handwriting-ocr-mcp-server": {
      "url": "https://mcp.handwriting-ocr.example.com/mcp",
      "headers": {
        "API_TOKEN": "<API_TOKEN>"
      }
    }
  }
}

You can run the Handwriting OCR MCP Server to connect MCP clients with the Handwriting OCR service. This server lets you upload images or PDFs, monitor processing status, and retrieve OCR results in Markdown format, enabling seamless automation and integration in your apps.

How to use

You use an MCP client to interact with the Handwriting OCR MCP Server by performing three core actions: upload a document (image or PDF), check the processing status, and fetch the OCR result as Markdown. Set your API token in the server environment to authenticate requests. Once running, your client can queue documents, poll for status updates, and receive formatted OCR output that you can display or store in your workflow.

How to install

Prerequisites you need before installation are Node.js version 18.x or higher and an active Handwriting OCR Platform account with a valid API token.

# Install the MCP server via Smithery for Claude Desktop
npx -y @smithery/cli install @Handwriting-OCR/handwriting-ocr-mcp-server --client claude

If you prefer manual setup for Claude Desktop, you can configure the MCP server directly in your client’s settings with the following example configuration. This runs the MCP server locally via Node and exposes your API token for authentication.

{
  "mcpServers": {
    "handwriting_ocr": {
      "command": "node",
      "args": [
        "/Users/mateo/Local/Code/MCP/handwriting-ocr/build/index.js"
      ],
      "env": {
        "API_TOKEN": "your-api-token",
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Additional sections

Configuration details are provided below to help you run the server securely and reliably. The server uses an API token for authentication and can be configured through environment variables. If you are deploying in a shared environment, consider securing the token with your platform’s secret management features.

Security tip: Treat the API token as a secret. Do not commit it to source control. Use your deployment platform’s secret storage and inject the token at runtime.

If you run into issues, verify that your API token is valid and that the Node.js process has network access to the Handwriting OCR Platform. If problems persist, submit a GitHub Issue for targeted support.

Available tools

Upload Document

Uploads an image or PDF for OCR processing and returns an initial processing reference.

Check Status

Polls or queries the current processing status for an uploaded document.

Get Text

Retrieves the OCR result formatted as Markdown once processing completes.