MCP Jena

🚀 Apache Jena's MCP Server

A Model Context Protocol (MCP) server that allows AI agents to perform SPARQL queries via Apache Jena.

🚀 Quick Start

The MCP server in this project enables AI agents (such as Cursor, Claude for Cline, or Claude Desktop) to access and query RDF data stored in Apache Jena. It provides tools for executing SPARQL queries and update operations.

✨ Features

• Execute SPARQL queries against the Jena Fuseki server.
• Perform SPARQL updates to modify RDF data.
• List available named graphs in the dataset.
• Support HTTP Basic authentication for Jena Fuseki.
• Be compatible with the Model Context Protocol.

📦 Prerequisites

• Node.js (v16 or higher).
• A running Apache Jena Fuseki server loaded with RDF data.
• AI agents supporting the Model Context Protocol (e.g., Cursor, Claude for Cline).

📦 Installation

1. Clone this repository:

   git clone https://github.com/ramuzes/mcp-jena.git
   cd mcp-jena
   

2. Install dependencies:

   npm install
   

3. Build the TypeScript code:

   npm run build
   

💻 Usage Examples

Basic Usage

Run the server with default settings (Jena address: localhost:3030, dataset name: ds):

npm start

Advanced Usage

Specify a custom Jena endpoint, dataset, and authentication credentials:

npm start -- --endpoint http://your-jena-server:3030 --dataset your_dataset --username your_username --password your_password

You can also use short flags:

npm start -- -e http://your-jena-server:3030 -d your_dataset -u your_username -p your_password

Run in development mode with automatic transpilation:

npm run dev:transpile -- -e http://your-jena-server:3030 -d your_dataset -u your_username -p your_password

📚 Documentation

Available Tools

This MCP server provides the following tools:

1. execute_sparql_query - Execute a SPARQL query against the Jena dataset.
2. execute_sparql_update - Execute a SPARQL update query to modify the dataset.
3. list_graphs - List all available named graphs in the dataset.

Environment Variables

You can also configure the server via environment variables:

• JENA_FUSEKI_URL: The URL of the Jena Fuseki server (default: http://localhost:3030).
• DEFAULT_DATASET: The default dataset name (default: ds).
• JENA_USERNAME: The HTTP Basic authentication username for accessing Jena Fuseki.
• JENA_PASSWORD: The HTTP Basic authentication password.
• PORT: The port of the MCP server (default for HTTP transport: 8080).
• API_KEY: The authentication API key for the MCP server.

Example SPARQL Queries

Basic SELECT Query:

SELECT ?subject ?predicate ?object
WHERE {
  ?subject ?predicate ?object
}
LIMIT 10

UPDATE Query to Insert Data:

PREFIX ex: <http://example.org/>
INSERT DATA {
  ex:subject1 ex:predicate1 "object1" .
  ex:subject2 ex:predicate2 42 .
}

Query a Specific Named Graph:

SELECT ?subject ?predicate ?object
FROM NAMED <http://example.org/graph1>
WHERE {
  GRAPH <http://example.org/graph1> {
    ?subject ?predicate ?object
  }
}
LIMIT 10

📚 Resources

• Model Context Protocol (MCP)
• Apache Jena
• Node.js