RDF Explorer

🚀 RDF Explorer v1.0.0

RDF Explorer is a Model Context Protocol (MCP) server that enables exploration and analysis of knowledge graphs (in RDF format) through a conversational interface, supporting both local file mode and SPARQL endpoint mode. It facilitates interaction between AI and knowledge graphs, allowing users to query, analyze, and manipulate RDF data using natural language processing techniques.

🚀 Quick Start

RDF Explorer is a Model Context Protocol (MCP) server that provides a conversational interface for exploring and analyzing knowledge graphs in RDF format. It supports both local file mode and SPARQL endpoint mode, enabling seamless interaction between AI and knowledge graphs. Users can easily retrieve information or perform complex data operations from the knowledge graph through question-and-answer sessions.

✨ Features

Tools

Feature List

• Local File Mode: Supports loading and parsing local RDF files in Turtle format.
• SPARQL Endpoint Mode: Supports connecting to remote SPARQL services for data querying.
• Data Query: Supports retrieving data from the knowledge graph using natural language or direct query syntax.
• Data Analysis: Provides analysis capabilities for the knowledge graph structure and entity relationships.
• Context Management: Maintains conversation context, supporting multi-round interactions.
• Result Formatting: Supports presenting query results in various formats (text, table, JSON, etc.).

Input and Output Definitions

• Input:
  • Natural language questions or SPARQL query statements.
  • Optional parameters include:
    • --triple-file: Path to the local RDF file.
    • --sparql-endpoint: URL of the remote SPARQL endpoint.
• Output:
  • Results are presented in a user-friendly format.
  • Supports JSON format output for programmatic processing.

Resources

Example Configurations

Configuration example for local file mode:

{
  "mcpServers": {
    "rdf_explorer": {
      "command": "C:\\path\\to\\venv\\Scripts\\python.exe",
      "args": ["C:\\path\\to\\server.py", "--triple-file", "your_file.ttl"]
    }
  }
}

Configuration example for SPARQL endpoint mode:

{
  "mcpServers": {
    "rdf_explorer": {
      "command": "C:\\path\\to\\venv\\Scripts\\python.exe",
      "args": ["C:\\path\\to\\server.py", "--sparql-endpoint", "https://example.com/sparql"]
    }
  }
}

Tips

Example Usage

Questions you can ask in local file mode:

• "Show all employees in the sales department."
• "Find the top five oldest customers."
• "Who bought more than three products?"
• "List all entities."
• "Using the DBpedia endpoint, list 10 songs by Michael Jackson."
• "Using the Wikidata endpoint, list 5 cities."
• "Count the number of triples."
• "Analyze the knowledge graph structure."
• "Select ..."
• "Search '{text}'."
• "Find the relationships of '{URI}'."
• "What mode is the RDF Explorer running in?"

Questions you can ask in SPARQL endpoint mode:

• "Using the DBpedia endpoint, list 10 songs by Michael Jackson."
• "Using the Wikidata endpoint, list 5 cities."
• "Select ..."
• "Search '{text}'."
• "Find the relationships of '{URI}'."
• "What mode is the RDF Explorer running in?"

💻 Usage Examples

Basic Usage

# Clone the repository
git clone https://github.com/emekaokoye/mcp-rdf-explorer.git
cd mcp-rdf-explorer

# Initialize the virtual environment
python -m venv venv
source venv/bin/activate
# Windows: venv\Scripts\activate

# Install development dependencies
pip install -r requirements.txt

# Run tests
pytest test_rdf_explorer.py -v

📄 License

This MCP server is released under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.