MCP GraphDB

MCP GraphDB

By keonchennl GitHub

A Model Context Protocol server that provides read only access to graphs in a certain repository in Ontotext GraphDB. This server enables LLMs to execute SPARQL queries. #database

mcp-graphdb sparql
Overview

what is MCP GraphDB?

MCP GraphDB is a Model Context Protocol server that provides read-only access to graphs stored in Ontotext GraphDB, enabling LLMs to execute SPARQL queries against a GraphDB instance.

how to use MCP GraphDB?

To use MCP GraphDB, configure the server with your GraphDB endpoint and repository details, then execute SPARQL queries to retrieve data from the connected GraphDB repository.

key features of MCP GraphDB?

  • Execute SPARQL queries in read-only mode.
  • List available graphs and their statistics.
  • Access various views of repository data, including class lists and sample data.

use cases of MCP GraphDB?

  1. Querying RDF graphs for research purposes.
  2. Integrating with LLMs for enhanced data retrieval.
  3. Analyzing graph data for insights in various domains.

FAQ from MCP GraphDB?

  • Can I modify the data in GraphDB using this server?

No, the server only allows read-only access to the data.

  • How do I configure the server?

You can configure it using environment variables or command-line arguments.

  • Is there a limit to the number of queries I can execute?

There is no specific limit, but performance may vary based on the complexity of the queries.

Content

# GraphDB MCP Server

A Model Context Protocol server that provides read-only access to Ontotext GraphDB. This server enables LLMs to explore RDF graphs and execute SPARQL queries against a GraphDB instance.

Components

Tools

  • **sparqlQuery**

    • Execute SPARQL queries against the connected GraphDB repository
    • Input:
      • `query` (string): The SPARQL query to execute
      • `graph` (string, optional): Specific graph IRI to target
      • `format` (string, optional): Response format (json, xml, csv)
    • All queries are executed in read-only mode
  • **listGraphs**

    • Lists all graphs available in the repository
    • No input parameters required

Resources

The server provides multiple views of the repository data:

  • **Class List** (`graphdb:///repository//classes`)

    • Lists all RDF classes found in the repository with counts
  • **Predicates** (`graphdb:///repository//predicates`)

    • Lists all predicates (properties) with usage counts
  • **Statistics** (`graphdb:///repository//stats`)

    • Provides counts of subjects, predicates, objects, and triples
  • **Sample Data** (`graphdb:///repository//sample`)

    • Shows a sample of triples from the repository
  • **Graph Content** (`graphdb:///repository//graph/`)

    • Provides sample data from specific graphs along with metadata

Configuration

You can configure the server using environment variables by creating a `.env` file:

``` GRAPHDB_ENDPOINT=http://localhost:7200 GRAPHDB_REPOSITORY=myRepository GRAPHDB_USERNAME=username GRAPHDB_PASSWORD=password ```

Alternatively, you can provide the endpoint and repository as command-line arguments:

``` node dist/index.js http://localhost:7200 myRepository ```

The command-line arguments take precedence over environment variables.

Usage with Claude Desktop

To use this server with the Claude Desktop app, add the following configuration to the "mcpServers" section of your `claude_desktop_config.json`:

```json { "mcpServers": { "graphdb": { "command": "node", "args": [ "/path/to/mcp-server-graphdb/dist/index.js" ], "env": { "GRAPHDB_ENDPOINT": "http://localhost:7200", "GRAPHDB_REPOSITORY": "myRepository", "GRAPHDB_USERNAME": "username", "GRAPHDB_PASSWORD": "password" } } } } ```

Replace the values with your specific GraphDB configuration.

Installation

```sh

Clone the repository

git clone https://github.com/yourname/mcp-server-graphdb.git cd mcp-server-graphdb

Install dependencies

yarn install

Build the project

yarn build ```

Example SPARQL Queries

Here are some example SPARQL queries you can run with this server:

  1. List all classes in the ontology: ```sparql PREFIX rdf: PREFIX rdfs: SELECT DISTINCT ?class ?label WHERE { { ?class a rdfs:Class } UNION { ?class a owl:Class } OPTIONAL { ?class rdfs:label ?label } } ORDER BY ?class ```

  2. List all properties for a specific class: ```sparql PREFIX rdf: PREFIX rdfs: SELECT ?property ?label ?range WHERE { ?property rdfs:domain . OPTIONAL { ?property rdfs:label ?label } OPTIONAL { ?property rdfs:range ?range } } ORDER BY ?property ```

  3. Count instances by class: ```sparql PREFIX rdf: SELECT ?class (COUNT(?instance) AS ?count) WHERE { ?instance a ?class } GROUP BY ?class ORDER BY DESC(?count) ```

License

This MCP server is licensed 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.

No tools information available.

An MCP server for querying SPARQL endpoint.

mcp-server sparql
View Details