RDF Explorer

by emekaokoye

13 stars

368 downloads

Not rated

GitHub

About

Enables conversational exploration and analysis of RDF Knowledge Graphs through SPARQL queries, full-text search, and visualization tools in both local file and endpoint modes.

Details

Author: emekaokoye
Repository: emekaokoye/mcp-rdf-explorer
GitHub stars: 13
Downloads: 368
License: MIT License
Categories: Productivity, Developer Tools, Design, File Management, AI, Search, Infrastructure, Other
Tags: #web, #analytics, #visualization

- Execute SPARQL queries on a local graph or external endpoint.
- Calculate graph statistics (triple count, unique subjects).
- Full‑text search across the graph or endpoint.
- Retrieve schema information (classes and properties).
- Run exploratory queries by name and generate Markdown reports.
- Convert natural language prompts into SPARQL queries.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name RDF Explorer

Command (node, npx, python, etc.) python
Arguments
- Argument 1 C:\path\to\server.py
- Argument 2 --triple-file
- Argument 3 your_file.ttl
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "C:\\path\\to\\venv\\Scripts\\python.exe"
        }
    }
}

JSON

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "python"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "C:\\path\\to\\venv\\Scripts\\python.exe"
        }
    }
}

JSON

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "python"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "C:\\path\\to\\venv\\Scripts\\python.exe"
        }
    }
}

JSON

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "python"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "C:\\path\\to\\venv\\Scripts\\python.exe"
        }
    }
}

JSON

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "python"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "C:\\path\\to\\venv\\Scripts\\python.exe"
        }
    }
}

JSON

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "python"
        }
    }
}

From the repository

Before starting make sure Claude Desktop is installed.
1. Go to: Settings > Developer > Edit Config

2. Add the following to your claude_desktop_config.json:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json

To use with a local RDF Turtle file, use this version with --triple-file args
``json { "mcpServers": { "rdf_explorer": { "command": "C:\\path\\to\\venv\\Scripts\\python.exe", "args": ["C:\\path\\to\\server.py", "--triple-file", "your_file.ttl"] } } }`To use with a SPARQL Endpoint, use this version with--sparql-endpointargs`json { "mcpServers": { "rdf_explorer": { "command": "C:\\path\\to\\venv\\Scripts\\python.exe", "args": ["C:\\path\\to\\server.py", "--sparql-endpoint", "https://example.com/sparql"] } } }``

3. Restart Claude Desktop and start querying and exploring graph data.

4. Prompt: "what mode is RDF Explorer running?"

Here are examples of how you can explore RDF data using natural language:

python -m venv venv
source venv/bin/activate

pip install -r requirements.txt

`execute_on_endpoint`

Execute a SPARQL query directly on an external endpoint. Parameters: endpoint (str), query (str), ctx (Context)

`sparql_query`

Execute a SPARQL query on the current graph or active external endpoint. Parameters: query (str), ctx (Context), use_service (bool)

`graph_stats`

Calculate and return statistics about the graph in JSON format. Parameters: ctx (Context)

`count_triples`

Count triples in the graph. Disabled in SPARQL Endpoint Mode. Parameters: ctx (Context)

`full_text_search`

Perform a full-text search on the graph or endpoint. Parameters: search_term (str), ctx (Context)

`health_check`

Check the health of the triplestore connection. Parameters: ctx (Context)

`get_mode`

Get the current mode of RDF Explorer. Parameters: ctx (Context)

`analyze_graph_structure`

Initiate an analysis of the graph structure with schema data.

`find_relationships`

Generate a SPARQL query to find relationships for a given subject.

`text_to_sparql`

Convert a text prompt to a SPARQL query and execute it. Parameters: prompt (str)

The server implements SPARQL queries and search functionality:

- execute_on_endpoint
- Execute a SPARQL query directly on an external endpoint
- Input:
- endpoint (str): The SPARQL endpoint URL to query.
- query (str): The SPARQL query to execute.
- ctx (Context): The FastMCP context object.
- Returns: Query results as a newline-separated string, or an error message.

- sparql_query
- Execute a SPARQL query on the current graph or active external endpoint
- Input:
- query (str): The SPARQL query to execute.
- ctx (Context): The FastMCP context object.
- use_service (bool): Whether to use a SERVICE clause for federated queries in local mode (default: True).
- Returns: Query results as a newline-separated string, or an error message.

- graph_stats
- Calculate and return statistics about the graph in JSON format
- Input:
- ctx (Context): The FastMCP context object.
- Returns: JSON string containing graph statistics (e.g., triple count, unique subjects).

- count_triples
- Count triples in the graph. Disabled in SPARQL Endpoint Mode; use a custom prompt instead.
- Input:
- ctx (Context): The FastMCP context object.
- Returns: Number of triples as a string, or an error message.

- full_text_search
- Perform a full-text search on the graph or endpoint, avoiding proprietary syntax.
- Input:
- search_term (str): The term to search for.
- ctx (Context): The FastMCP context object.
- Returns: Search results as a newline-separated string, or an error message.

- health_check
- Check the health of the triplestore connection.
- Input:
- ctx (Context): The FastMCP context object.
- Returns: 'Healthy' if the connection is good, 'Unhealthy: <error>' otherwise.

- get_mode
- Get the current mode of RDF Explorer. Useful for knowledge graph and semantic tech users to verify data source.
- Input:
- ctx (Context): The FastMCP context object.
- Returns: A message indicating the mode and dataset or endpoint.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "rdf explorer": {
            "cwd": null,
            "env": {},
            "args": [
                "C:\\path\\to\\server.py",
                "--triple-file",
                "your_file.ttl"
            ],
            "shell": false,
            "command": "python"
        }
    }
}

Linux

{
    "cwd": null,
    "env": [],
    "args": [
        "C:\\path\\to\\server.py",
        "--triple-file",
        "your_file.ttl"
    ],
    "shell": false,
    "command": "python"
}

Macos

{
    "cwd": null,
    "env": [],
    "args": [
        "C:\\path\\to\\server.py",
        "--triple-file",
        "your_file.ttl"
    ],
    "shell": false,
    "command": "python"
}

Windows

{
    "cwd": null,
    "env": [],
    "args": [
        "C:\\path\\to\\server.py",
        "--triple-file",
        "your_file.ttl"
    ],
    "shell": false,
    "command": "C:\\path\\to\\venv\\Scripts\\python.exe"
}

RDF Explorer v1.0.0

Overview

A Model Context Protocol (MCP) server that provides conversational interface for the exploration and analysis of RDF (Turtle) based Knowledge Graph in Local File mode or SPARQL Endpoint mode. This server facilitates communication between AI applications (hosts/clients) and RDF data, making graph exploration and analyzing graph data through SPARQL queries. A perfect tool for knowledge graph research and AI data preparation.

Components

Tools

The server implements SPARQL queries and search functionality: - execute_on_endpoint - Execute a SPARQL query directly on an external endpoint - Input: - endpoint (str): The SPARQL endpoint URL to query. - query (str): The SPARQL query to execute. - ctx (Context): The FastMCP context object. - Returns: Query results as a newline-separated string, or an error message. - sparql_query - Execute a SPARQL query on the current graph or active external endpoint - Input: - query (str): The SPARQL query to execute. - ctx (Context): The FastMCP context object. - use_service (bool): Whether to use a SERVICE clause for federated queries in local mode (default: True). - Returns: Query results as a newline-separated string, or an error message. - graph_stats - Calculate and return statistics about the graph in JSON format - Input: - ctx (Context): The FastMCP context object. - Returns: JSON string containing graph statistics (e.g., triple count, unique subjects). - count_triples - Count triples in the graph. Disabled in SPARQL Endpoint Mode; use a custom prompt instead. - Input: - ctx (Context): The FastMCP context object. - Returns: Number of triples as a string, or an error message. - full_text_search - Perform a full-text search on the graph or endpoint, avoiding proprietary syntax. - Input: - search_term (str): The term to search for. - ctx (Context): The FastMCP context object. - Returns: Search results as a newline-separated string, or an error message. - health_check - Check the health of the triplestore connection. - Input: - ctx (Context): The FastMCP context object. - Returns: 'Healthy' if the connection is good, 'Unhealthy: <error>' otherwise. - get_mode - Get the current mode of RDF Explorer. Useful for knowledge graph and semantic tech users to verify data source. - Input: - ctx (Context): The FastMCP context object. - Returns: A message indicating the mode and dataset or endpoint.

Resources

The server exposes the following resources: - schema://all: Retrieve schema information (classes and properties) from the graph. - Returns: A newline-separated string of schema elements (classes and properties). - queries://{template_name}: Retrieve a predefined SPARQL query template by name. - Returns: The SPARQL query string or 'Template not found'. - explore://{query_name}: Execute an exploratory SPARQL query by name and return results in JSON. - query_name (str): The name of the exploratory query (e.g., 'classes', 'relationships/URI'). - Returns: JSON string of query results. - explore://report: Generate a Markdown report of exploratory queries. - Returns: A Markdown-formatted report string.

Prompts

The server exposes the following prompts: - analyze_graph_structure: Initiate an analysis of the graph structure with schema data. - Returns: A list of messages to guide graph structure analysis. - find_relationships: Generate a SPARQL query to find relationships for a given subject. - Returns: A SPARQL query string to find relationships. - text_to_sparql: Convert a text prompt to a SPARQL query and execute it, with token limit checks. - prompt (str): The text prompt to convert to SPARQL. - Returns: Query results with usage stats, or an error message.

Setup

Configuration

Installing on Claude Desktop

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



To use with a SPARQL Endpoint, use this version with

--sparql-endpoint

 args

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



3. Restart Claude Desktop and start querying and exploring graph data.

4. Prompt: "what mode is RDF Explorer running?"




Usage Examples


Here are examples of how you can explore RDF data using natural language:

Querying Data in Local File Mode


You can ask questions like:
- "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" 
- "Using the DBpedia endpoint, list 10 songs by Michael Jackson" 
- "Using the Wikidata endpoint, list 5 cities"
- "count the triples"
- "analyze the graph structure"
- "Select ..."
- "search '{text}' "
- "find relationships of '{URI}'"
- "what mode is RDF Explorer running?"

Querying Data in SPARQL Endpoint Mode


You can ask questions like:
- "Using the DBpedia endpoint, list 10 songs by Michael Jackson" 
- "Using the Wikidata endpoint, list 5 cities"
- "Select ..."
- "search '{text}' "
- "find relationships of '{URI}'"
- "what mode is RDF Explorer running?"

Development

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

execute_on_endpoint

sparql_query

graph_stats

count_triples

full_text_search

health_check

get_mode

analyze_graph_structure

find_relationships

text_to_sparql

Claude Desktop / Cursor

Linux

Macos

Windows

RDF Explorer v1.0.0

Overview

Components

Tools

Resources

Prompts

Setup

Configuration

Installing on Claude Desktop

Usage Examples

Querying Data in Local File Mode

Querying Data in SPARQL Endpoint Mode

Development

Install

More like this

Time

Sentry

Github

Git

GitLab

Context 7

`execute_on_endpoint`

`sparql_query`

`graph_stats`

`count_triples`

`full_text_search`

`health_check`

`get_mode`

`analyze_graph_structure`

`find_relationships`

`text_to_sparql`