Skip to content

GroupDocs.Parser Cloud MCP server that gives AI assistants the power to parse text, barcodes, and images from 50+ document formats and format families (PDF, Word, Excel) using the robust GroupDocs.Parser Cloud API.

License

Notifications You must be signed in to change notification settings

groupdocs-parser-cloud/groupdocs-parser-cloud-mcp

Repository files navigation

GroupDocs.Parser Cloud MCP Server

Python Version License GroupDocs.Cloud MCP Compatible

A lightweight MCP (Model Context Protocol) server that wraps GroupDocs.Parser Cloud API to provide document-parsing capabilities to AI agents, assistants, and development environments.

It enables LLMs to extract text, images, and barcodes from documents stored in GroupDocs Cloud storage, and provides shared cloud storage utilities (upload, download, list, exists, delete).


🔧 Features

  • Lightweight GroupDocs.Parser Cloud MCP server
  • Document parsing via GroupDocs.Parser Cloud:
    • Extract plain text
    • Extract images
    • Extract barcodes
  • Supports 50+ document formats (PDF, Word, Excel, PowerPoint, emails, archives, images, and more)
  • Cross-platform: Windows, macOS, Linux

🚀 Quick Start

This section explains how to configure and run the GroupDocs.Parser Cloud MCP server

1. Clone the repository

git clone git@github.com:groupdocs-parser-cloud/groupdocs-parser-cloud-mcp.git
cd groupdocs-parser-cloud-mcp

2. Configure environment variables

Create a .env file with your settings.
You can either create it manually or copy the .env.example file.

CLIENT_ID=your-client-id
CLIENT_SECRET=your-client-secret
MCP_PORT=8000

Get credentials at:
https://dashboard.groupdocs.cloud/#/applications

3. Run the server

Bash / macOS / Linux

./run.sh

Windows (PowerShell):

.\run.ps1

Windows (CMD):

run.bat

Server starts at:

http://localhost:8000/mcp

🧩 How to use the MCP server in your environments, agents, and assistants

This section describes integration examples.


Test with @modelcontextprotocol/inspector

  1. Run the inspector:
    npx @modelcontextprotocol/inspector
  2. In the browser:
    • Select “streamable HTTP”
    • Enter your MCP URL:
      http://127.0.0.1:8000/mcp
      
    • Click Connect

📘 Using the MCP server in VSCode

  1. Create .vscode/mcp.json:
{
  "servers": {
    "groupdocs-parser-mcp-local": {
      "type": "http",
      "url": "http://127.0.0.1:8000/mcp"
    }
  }
}
  1. Restart VSCode if required.
    Now the MCP server is available inside VSCode’s MCP-enabled environments.

🤖 Using the MCP server with KiloCode

  1. Open KiloCode Settings → MCP Servers
  2. Open the Installed tab
  3. Edit “Project MCP”
  4. Add the config:
{
  "mcpServers": {
    "groupdocs-parser-mcp-local": {
      "type": "streamable-http",
      "url": "http://127.0.0.1:8000/mcp"
    }
  }
}
  1. Add a test file such as info.pdf
  2. Example prompt:

Extract text from info.pdf using Groupdocs.Parser MCP and briefly summarize the document.


🧠 Using the MCP server with Cursor

To use this MCP server with Cursor, configure the mcp.json file in your Cursor settings.

  1. Open Cursor Settings at the right top corner of the window
  2. Navigate to Tools & MCP section
  3. Click Add Custom MCP
  4. Locate or create the mcp.json configuration section and add the following configuration:
{
  "mcpServers": {
    "groupdocs-parser-mcp-local": {
      "url": "http://127.0.0.1:8000/mcp"
    }
  }
}
  1. In a Cursor chat, feel free to reference documents stored in GroupDocs.Cloud or ask to process local documents so they can be uploaded to GroupDocs.Cloud. For example, use prompts such as:

Extract text from [your-folder]\a-book.epub with GroupDocs.Parser MCP and summarize the information from the e-book.


Troubleshooting and Advanced Options

Reinitialize the Virtual Environment

If you update the codebase and the MCP server stops working due to missing dependencies (for example, after adding new packages to requirements.txt), you may need to fully reinitialize the local virtual environment.

To do this, use the init_mcp script for your platform:

Linux / macOS / Bash

./init_mcp.sh

Windows PowerShell

.\init_mcp.ps1

Windows CMD

init_mcp.bat

What this command does

The init_mcp script performs a full reset:

  1. Removes the existing .venv directory
  2. Creates a fresh virtual environment
  3. Installs all dependencies from requirements.txt
  4. Prepares the environment so run_mcp.* can start the server normally

After reinitialization, simply start the server again:

Bash / macOS / Linux

./run_mcp.sh

PowerShell

.\run_mcp.ps1

CMD

run_mcp.bat

This ensures your environment is always in sync with the current project requirements.

📄 License

This project is licensed under MIT License.

About

GroupDocs.Parser Cloud MCP server that gives AI assistants the power to parse text, barcodes, and images from 50+ document formats and format families (PDF, Word, Excel) using the robust GroupDocs.Parser Cloud API.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •