TextIn OCR

Provides OCR, text extraction, and Markdown conversion for documents via MCP workflows.

javascript

27

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months 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": {
    "intsig-textin-textin-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@intsig/server-textin"
      ],
      "env": {
        "APP_ID": "<YOUR_APP_ID>",
        "APP_SECRET": "<YOUR_APP_SECRET>",
        "MCP_SERVER_REQUEST_TIMEOUT": "600000"
      }
    }
  }
}

TextIn OCR MCP Server provides text extraction and OCR capabilities on documents, including ID and invoice recognition, with the ability to convert documents into Markdown. It is designed to be used from an MCP client to process inputs and return structured text or markdown outputs.

How to use

You integrate this MCP server into your MCP client workflow to perform text recognition, information extraction, and Markdown conversion on documents. Use the server to process inputs such as images, PDFs, or Word documents and receive structured text, extracted fields, or Markdown output.

Typical usage patterns include: recognizing text from documents to index content, extracting key fields like identifiers or dates from documents, and converting documents into Markdown for easy readability. For each request you can specify different tools like recognition_text, doc_to_markdown, and general_information_extration via your MCP client, and the server will return the appropriate results.

How to install

Prerequisites: ensure you have a modern Node.js and npm setup. You may also use npm or npx to configure and run the MCP server.

Create your MCP configuration to run the TextIn OCR MCP Server via npx. Use the following configuration snippet as your runtime definition.

{
  "mcpServers": {
    "textin_ocr": {
      "command": "npx",
      "args": [
        "-y",
        "@intsig/server-textin"
      ],
      "env": {
        "APP_ID": "<YOUR_APP_ID>",
        "APP_SECRET": "<YOUR_APP_SECRET>",
        "MCP_SERVER_REQUEST_TIMEOUT": "600000"
      },
      "timeout": 600
    }
  }
}

Additional notes

This MCP server supports three tools: recognition_text for text extraction from images, Word documents, and PDFs; doc_to_markdown for converting documents to Markdown; and general_information_extration for identifying and extracting key information from documents.

Available tools

recognition_text

Recognizes text from images, Word documents, and PDFs, returning the extracted text.

doc_to_markdown

Converts images, PDFs, and Word documents to Markdown output.

general_information_extration

Automatically identifies and extracts key information from documents or user-specified fields, returning a JSON with the extracted data.