MCP-Ragdocs

A Model Context Protocol (MCP) server that enables semantic search and retrieval of documentation using a vector database (Qdrant). This server allows you to add documentation from URLs or local files and then search through them using natural language queries.

Quick Install Guide

Install the package globally:

npm install -g @qpd-v/mcp-server-ragdocs

Start Qdrant (using Docker):

docker run -p 6333:6333 -p 6334:6334 qdrant/qdrant

Ensure Ollama is running with the default embedding model:
```
ollama pull nomic-embed-text
```

Add to your configuration file:

For Cline: %AppData%\Roaming\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json
For Roo-Code: %AppData%\Roaming\Code\User\globalStorage\rooveterinaryinc.roo-cline\settings\cline_mcp_settings.json
For Claude Desktop: %AppData%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "ragdocs": {
      "command": "node",
      "args": ["C:/Users/YOUR_USERNAME/AppData/Roaming/npm/node_modules/@qpd-v/mcp-server-ragdocs/build/index.js"],
      "env": {
        "QDRANT_URL": "http://127.0.0.1:6333",
        "EMBEDDING_PROVIDER": "ollama",
        "OLLAMA_URL": "http://localhost:11434"
      }
    }
  }
}

Verify installation:

# Check Qdrant is running
curl http://localhost:6333/collections

# Check Ollama has the model
ollama list | grep nomic-embed-text

Version

Current version: 0.1.6

Features

Add documentation from URLs or local files
Store documentation in a vector database for semantic search
Search through documentation using natural language
List all documentation sources

Installation

Install globally using npm:

npm install -g @qpd-v/mcp-server-ragdocs

This will install the server in your global npm directory, which you'll need for the configuration steps below.

Requirements

Node.js 16 or higher
Qdrant (either local or cloud)
One of the following for embeddings:
- Ollama running locally (default, free)
- OpenAI API key (optional, paid)

Qdrant Setup Options

Option 1: Local Qdrant

Using Docker (recommended):

docker run -p 6333:6333 -p 6334:6334 qdrant/qdrant

Or download from Qdrant's website

Option 2: Qdrant Cloud

Create an account at Qdrant Cloud
Create a new cluster
Get your cluster URL and API key from the dashboard
Use these in your configuration (see Configuration section below)

Configuration

The server can be used with both Cline/Roo and Claude Desktop. Configuration differs slightly between them:

Cline Configuration

Add to your Cline settings file (%AppData%\Roaming\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json) AND/OR Add to your Roo-Code settings file (%AppData%\Roaming\Code\User\globalStorage\rooveterinaryinc.roo-cline\settings\cline_mcp_settings.json):

Using npm global install (recommended):

{
		"mcpServers": {
				"ragdocs": {
						"command": "node",
      "args": ["C:/Users/YOUR_USERNAME/AppData/Roaming/npm/node_modules/@qpd-v/mcp-server-ragdocs/build/index.js"],
      "env": {
        "QDRANT_URL": "http://127.0.0.1:6333",
        "EMBEDDING_PROVIDER": "ollama",
        "OLLAMA_URL": "http://localhost:11434"
      }
    }
  }
}

For OpenAI instead of Ollama:

{
		"mcpServers": {
				"ragdocs": {
						"command": "node",
      "args": ["C:/Users/YOUR_USERNAME/AppData/Roaming/npm/node_modules/@qpd-v/mcp-server-ragdocs/build/index.js"],
      "env": {
        "QDRANT_URL": "http://127.0.0.1:6333",
        "EMBEDDING_PROVIDER": "openai",
        "OPENAI_API_KEY": "your-openai-api-key"
      }
    }
  }
}

Using local development setup:

{
		"mcpServers": {
				"ragdocs": {
						"command": "node",
						"args": ["PATH_TO_PROJECT/mcp-ragdocs/build/index.js"],
						"env": {
								"QDRANT_URL": "http://127.0.0.1:6333",
								"EMBEDDING_PROVIDER": "ollama",
								"OLLAMA_URL": "http://localhost:11434"
						}
				}
		}
}

Claude Desktop Configuration

Add to your Claude Desktop config file:

Windows: %AppData%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows Setup with Ollama (using full paths):

{
  "mcpServers": {
    "ragdocs": {
      "command": "C:\\Program Files\\nodejs\\node.exe",
      "args": [
        "C:\\Users\\YOUR_USERNAME\\AppData\\Roaming\\npm\\node_modules\\@qpd-v/mcp-server-ragdocs\\build\\index.js"
      ],
      "env": {
								"QDRANT_URL": "http://127.0.0.1:6333",
								"EMBEDDING_PROVIDER": "ollama",
								"OLLAMA_URL": "http://localhost:11434"
						}
				}
		}
}

Windows Setup with OpenAI:

{
		"mcpServers": {
				"ragdocs": {
						"command": "C:\\Program Files\\nodejs\\node.exe",
						"args": [
								"C:\\Users\\YOUR_USERNAME\\AppData\\Roaming\\npm\\node_modules\\@qpd-v/mcp-server-ragdocs\\build\\index.js"
						],
						"env": {
								"QDRANT_URL": "http://127.0.0.1:6333",
								"EMBEDDING_PROVIDER": "openai",
								"OPENAI_API_KEY": "your-openai-api-key"
						}
				}
		}
}

macOS Setup with Ollama:

{
		"mcpServers": {
				"ragdocs": {
						"command": "/usr/local/bin/node",
						"args": [
								"/usr/local/lib/node_modules/@qpd-v/mcp-server-ragdocs/build/index.js"
						],
						"env": {
								"QDRANT_URL": "http://127.0.0.1:6333",
								"EMBEDDING_PROVIDER": "ollama",
								"OLLAMA_URL": "http://localhost:11434"
						}
				}
		}
}

Qdrant Cloud Configuration

For either Cline or Claude Desktop, when using Qdrant Cloud, modify the env section:

With Ollama:

{
		"env": {
				"QDRANT_URL": "https://your-cluster-url.qdrant.tech",
				"QDRANT_API_KEY": "your-qdrant-api-key",
				"EMBEDDING_PROVIDER": "ollama",
				"OLLAMA_URL": "http://localhost:11434"
		}
}

With OpenAI:

{
		"env": {
				"QDRANT_URL": "https://your-cluster-url.qdrant.tech",
				"QDRANT_API_KEY": "your-qdrant-api-key",
				"EMBEDDING_PROVIDER": "openai",
				"OPENAI_API_KEY": "your-openai-api-key"
		}
}

Environment Variables

Qdrant Configuration

QDRANT_URL (required): URL of your Qdrant instance
- For local: http://localhost:6333
- For cloud: https://your-cluster-url.qdrant.tech
QDRANT_API_KEY (required for cloud): Your Qdrant Cloud API key

Embeddings Configuration

EMBEDDING_PROVIDER (optional): Choose between 'ollama' (default) or 'openai'
EMBEDDING_MODEL (optional):
- For Ollama: defaults to 'nomic-embed-text'
- For OpenAI: defaults to 'text-embedding-3-small'
OLLAMA_URL (optional): URL of your Ollama instance (defaults to http://localhost:11434)
OPENAI_API_KEY (required if using OpenAI): Your OpenAI API key

Available Tools

add_documentation
- Add documentation from a URL to the RAG database
- Parameters:
  - url: URL of the documentation to fetch
search_documentation
- Search through stored documentation
- Parameters:
  - query: Search query
  - limit (optional): Maximum number of results to return (default: 5)
list_sources
- List all documentation sources currently stored
- No parameters required

Example Usage

In Claude Desktop or any other MCP-compatible client:

Add documentation:

Add this documentation: https://docs.example.com/api

Search documentation:

Search the documentation for information about authentication

List sources:

What documentation sources are available?

Development

Clone the repository:

git clone https://github.com/qpd-v/mcp-server-ragdocs.git
cd mcp-server-ragdocs

Install dependencies:

npm install

Build the project:

npm run build

Run locally:

npm start

License

MIT

Troubleshooting

Common Issues

Qdrant Connection Error
```
Error: Failed to connect to Qdrant at http://localhost:6333
```
- Check if Docker is running
- Verify Qdrant container is running: docker ps | grep qdrant
- Try restarting the container
Ollama Model Missing
```
Error: Model nomic-embed-text not found
```
- Run: ollama pull nomic-embed-text
- Verify model is installed: ollama list
Configuration Path Issues
- Windows: Replace YOUR_USERNAME with your actual Windows username
- Check file permissions
- Verify the paths exist
npm Global Install Issues
- Try installing with admin privileges
- Check npm is in PATH: npm -v
- Verify global installation: npm list -g @qpd-v/mcp-server-ragdocs

For other issues, please check:

Docker logs: docker logs $(docker ps -q --filter ancestor=qdrant/qdrant)
Ollama status: ollama list
Node.js version: node -v (should be 16 or higher)

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

MCP-RAGDocs