GroundX RAG MCP server

Integrates with GroundX to provide document search and ingestion capabilities, enabling domain-specific knowledge retrieval without requiring direct access to underlying document storage.
Back to servers
Setup instructions
Provider
PRIXYY
Release date
Apr 13, 2025
Language
Python
Stats
1 star

This MCP server enables document ingestion and question-answering capabilities powered by the GroundX API. It allows you to upload documents and then ask questions that will be answered based on the content of those documents.

Getting Started

Prerequisites

Before you begin, you'll need:

  • A GroundX API key
  • Cursor text editor installed

Installation Steps

  1. Fork the repository to your GitHub account
  2. Open the forked repository in Cursor
  3. Configure your GroundX API key in the server.py file:
# server.py
GROUNDX_API_KEY = "your_api_key_here"
  1. Use the "Add MCP" option in Cursor
    • The platform will automatically detect the included mcp.json file

Using the MCP Server

Available Tools

Once your MCP server is properly configured and running, you'll have access to two main tools:

  1. Document Ingestion Tool

    • Tool name: ingest_documents
    • Purpose: Upload new documents to the system for analysis
  2. Question Answering Tool

    • Tool name: answer_query
    • Purpose: Ask questions about the ingested documents and receive context-aware answers

Workflow

The typical workflow involves:

  1. First ingesting your documents using the ingest_documents tool
  2. Then using the answer_query tool to ask questions about those documents
  3. The system will provide answers based on the content found in your uploaded documents

All questions will be processed using the GroundX API which handles the document parsing and intelligence features to provide relevant responses.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "groundx-rag" '{"command":"python","args":["server.py"]}'

See the official Claude Code MCP documentation for more details.

For 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 > Tools & Integrations and click "New MCP Server".

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

{
    "mcpServers": {
        "groundx-rag": {
            "command": "python",
            "args": [
                "server.py"
            ]
        }
    }
}

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 explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "groundx-rag": {
            "command": "python",
            "args": [
                "server.py"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later