ragie-mcp-server

The Ragie Model Context Protocol Server implements the MCP to enable retrieval of information from the Ragie knowledge base. It provides a querying tool, allowing users to easily extract relevant information.

GitHub Stars

71

User Rating

Not Rated

Favorites

0

Views

31

Forks

16

Issues

1

Installation
Difficulty
Intermediate
Estimated Time
10-20 minutes
Requirements
Node.js >= 18

Installation

Installation

Prerequisites

Please specify required software and versions:
Node.js: 18.0.0 or higher

Installation Steps

1. Start the Server

Run the following command to start the server:
bash
RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server

2. Using Command Line Options

To specify a custom description or partition ID, run:
bash
RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server --description "Custom description" --partition your_partition_id

Troubleshooting

Common Issues

Issue: Server won't start Solution: Check Node.js version and reinstall dependencies.

Configuration

Configuration

Basic Configuration

Create MCP Configuration File

Create a file called mcp.json with the following content:
json
{
  "mcpServers": {
    "ragie": {
      "command": "npx",
      "args": ["-y", "@ragieai/mcp-server", "--partition", "optional_partition_id"],
      "env": {
        "RAGIE_API_KEY": "your_api_key"
      }
    }
  }
}

Setting Environment Variables

Set the following environment variable as needed:
bash
export RAGIE_API_KEY="your_api_key"

Security Settings

Store API keys in environment variables or secure configuration files.
Set appropriate file access permissions.

Examples

Examples

Basic Usage

Here are basic usage examples for the MCP server:

Programmatic Usage

javascript
// JavaScript example (Node.js)
const { MCPClient } = require('@modelcontextprotocol/client');

const client = new MCPClient();
await client.connect();

// Execute tool
const result = await client.callTool('toolName', {
  parameter1: 'value1',
  parameter2: 'value2'
});

console.log(result);

Script Usage

bash
#!/bin/bash

Batch processing example

for file in *.txt; do mcp-tool process "$file" done

Use Cases

Execute queries to search for specific information from a company's knowledge base.
Dynamically retrieve data needed by AI models using the MCP server.
Utilize a common MCP server configuration across multiple projects.
Run automated data processing using scripts.

Additional Resources