GraphDB MCP Server
The GraphDB MCP Server provides read-only access to an Ontotext GraphDB instance, enabling exploration of RDF graphs and execution of SPARQL queries.
Execute SPARQL queries: Run read-only SPARQL queries against the repository with optional graph targeting and response format selection.
List available graphs: Retrieve a list of all graphs in the repository.
View repository data: Access structured views including class lists, predicates, statistics, sample data, and specific graph content.
Custom configuration: Configure server parameters via environment variables or command-line arguments for flexible deployment.
Integration with Claude Desktop: Use with Claude Desktop app for enhanced functionality.
Supports configuration through environment variables in a .env file for GraphDB connection details including endpoint, repository, username, and password.
Allows installation of the MCP server through git clone from a repository.
Supports XML as one of the available response formats for SPARQL query results.
Used for package management, installing dependencies, and building the project.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@GraphDB MCP Server list all classes in the repository with their instance counts"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 executegraph(string, optional): Specific graph IRI to targetformat(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://<host>/repository/<repo>/classes)Lists all RDF classes found in the repository with counts
Predicates (
graphdb://<host>/repository/<repo>/predicates)Lists all predicates (properties) with usage counts
Statistics (
graphdb://<host>/repository/<repo>/stats)Provides counts of subjects, predicates, objects, and triples
Sample Data (
graphdb://<host>/repository/<repo>/sample)Shows a sample of triples from the repository
Graph Content (
graphdb://<host>/repository/<repo>/graph/<graphUri>)Provides sample data from specific graphs along with metadata
Related MCP server: RDF Explorer
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=passwordAlternatively, you can provide the endpoint and repository as command-line arguments:
node dist/index.js http://localhost:7200 myRepositoryThe 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:
{
"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
# Clone the repository
git clone https://github.com/keonchennl/mcp-server-graphdb.git
cd mcp-server-graphdb
# Install dependencies
yarn install
# Build the project
yarn buildExample SPARQL Queries
Here are some example SPARQL queries you can run with this server:
List all classes in the ontology:
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT DISTINCT ?class ?label
WHERE {
{ ?class a rdfs:Class } UNION { ?class a owl:Class }
OPTIONAL { ?class rdfs:label ?label }
}
ORDER BY ?classList all properties for a specific class:
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?property ?label ?range
WHERE {
?property rdfs:domain <http://example.org/YourClass> .
OPTIONAL { ?property rdfs:label ?label }
OPTIONAL { ?property rdfs:range ?range }
}
ORDER BY ?propertyCount instances by class:
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
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 GPL-3.0 License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the GNU GPL-3.0 License.
Available Tools
2 toolslistGraphsB
List all graphs in the repository
Inputs: no named parameters.
sparqlQueryA
Execute a read-only SPARQL query against the GraphDB repository
Inputs: query (required), format, graph.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one lists available graphs, while the other executes queries against them. There is no overlap in functionality, making it impossible to confuse their intended use.
Both tools use camelCase naming, which is consistent, but they follow different patterns: 'listGraphs' uses a verb-noun structure, while 'sparqlQuery' uses a noun-verb structure. This minor deviation prevents a perfect score.
With only two tools, the server feels thin for a GraphDB domain, lacking essential operations like creating, updating, or deleting graphs or data. This minimal set is insufficient for typical database workflows.
The server covers listing and querying but misses critical CRUD operations for a GraphDB system, such as creating graphs, inserting data, or modifying content. This creates significant gaps that will hinder agent tasks.
Maintenance
Related MCP Connectors
Repository knowledge graph MCP server for codebase understanding and debugging.
Query your own knowledge graph from any MCP client. The graph lives in a database you own.
The Grafbase MCP server sits in front of a GraphQL API and exposes an MCP protocol-compliant interface that allows AI agents and LLMs to explore and query GraphQL APIs using natural language. It provides tools to search schemas, introspect types and fields, and execute GraphQL queries while minimizing context bloat by returning only relevant schema subsets, with built-in support for authentication, authorization, and configurable access control.
A Model Context Protocol server for Wix AI tools
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that connects AI agents to Apache Jena, enabling them to execute SPARQL queries and updates against RDF data stored in Jena Fuseki.8MIT
- AlicenseNot gradedqualityCmaintenanceThe Model Context Protocol (MCP) server provides a conversational interface for the exploration and analysis of RDF Turtle Knowledge Graph in Local File mode or SPARQL Endpoint.56MIT
- AlicenseCqualityDmaintenanceA Model Context Protocol (MCP) server that connects GraphDB's SPARQL endpoints and Ollama models to Claude, enabling Claude to query and manipulate ontology data while leveraging various AI models.283MIT

Memgraph MCP Serverofficial
AlicenseCqualityNot gradedmaintenanceA lightweight server implementation of the Model Context Protocol that connects Memgraph database with LLMs, allowing users to interact with graph databases through natural language.125MIT