RDF Explorer MCP server

RDF Explorer is a Model Context Protocol (MCP) server that provides a conversational interface for exploring and analyzing RDF-based Knowledge Graphs. It supports two operating modes: Local File mode for processing local Turtle files and SPARQL Endpoint mode for querying remote SPARQL endpoints, making it an excellent tool for knowledge graph exploration and AI data preparation.

Installation and Configuration

Prerequisites

• Claude Desktop must be installed on your system

Setting Up RDF Explorer

1. Go to Settings > Developer > Edit Config in Claude Desktop

2. Add the following to your claude_desktop_config.json:

   • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%/Claude/claude_desktop_config.json

3. Choose one of the following configurations:

For local RDF Turtle file mode:

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

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"]
    }
  }
}

4. Restart Claude Desktop to apply the configuration

Using RDF Explorer

Checking Connection

To verify the connection and identify the current mode:

what mode is RDF Explorer running?

Basic Queries

RDF Explorer supports natural language queries that get converted to SPARQL:

Local File Mode Queries

• "Show me all employees in the Sales department"
• "Find the top 5 oldest customers"
• "Who has purchased more than 3 products in the last month?"
• "List all entities"
• "count the triples"
• "analyze the graph structure"

SPARQL Endpoint Mode Queries

• "Using the DBpedia endpoint, list 10 songs by Michael Jackson"
• "Using the Wikidata endpoint, list 5 cities"
• "Select ..."

Search Functions

To search for text in the graph:

search 'your search term'

Relationship Exploration

To find relationships of a specific URI:

find relationships of 'http://example.org/resource'

Direct SPARQL Queries

You can also execute SPARQL queries directly:

Select * WHERE {?s ?p ?o} LIMIT 10

Advanced Features

Graph Analysis

To analyze the graph structure:

analyze the graph structure

Federated Queries

RDF Explorer supports federated queries across multiple endpoints:

Using the DBpedia endpoint, list 10 songs by Michael Jackson

Graph Statistics

To get statistics about the loaded graph:

graph stats

Health Check

To verify the connection to the triplestore:

health check

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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