Ontosphere
Browser-based RDF/ontology knowledge graph editor — load RDF from files, URLs or SPARQL endpoints; author nodes and edges on the canvas; run OWL-RL reasoning; apply multi-algorithm layout and clustering. AI-native via MCP tool surface and relay bridg
What is Ontosphere?
Ontosphere is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to browser-based rdf/ontology knowledge graph editor — load rdf from files, urls or sparql endpoints; author nodes and edges on the canvas; run owl-rl reasoning; apply multi-algorithm layout and clusteri...
Browser-based RDF/ontology knowledge graph editor — load RDF from files, URLs or SPARQL endpoints; author nodes and edges on the canvas; run OWL-RL reasoning; apply multi-algorithm layout and clustering. AI-native via MCP tool surface and relay bridg
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Browser-based RDF/ontology knowledge graph editor — load RDF
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx ontosphereConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Ontosphere
Ontosphere is a browser-based RDF and ontology knowledge graph editor that exposes over 30 MCP tools so AI assistants can directly author and query semantic graphs. It can load RDF data from local files, remote URLs, or SPARQL endpoints, and supports OWL-RL reasoning, SHACL validation, and multiple layout and clustering algorithms. Researchers, knowledge engineers, and linked-data practitioners use Ontosphere to build, visualize, and interrogate ontologies entirely through natural language conversations with an AI model.
Prerequisites
- Node.js 18+ and npm installed for running the development server
- An MCP client such as Claude Desktop that supports MCP tool calls
- Basic understanding of RDF, OWL, or linked-data concepts
- Optional: a SPARQL endpoint URL or local RDF files in Turtle, JSON-LD, or RDF/XML format
Clone the Ontosphere repository
Clone the repository from GitHub and navigate into the project directory.
git clone https://github.com/ThHanke/ontosphere.git
cd ontosphereInstall dependencies and start the dev server
Install npm packages and launch the Vite development server. The app will open at http://localhost:8080/.
npm install
npm run devVerify the MCP tool surface is available
The MCP server manifest is served at the well-known path. Confirm it lists the expected tools before connecting your MCP client.
curl http://localhost:8080/.well-known/mcp.json | head -40Configure your MCP client to connect to Ontosphere
Ontosphere uses an SSE or relay bridge transport. Add the server URL to your MCP client configuration pointing at the running local instance.
{
"mcpServers": {
"ontosphere": {
"url": "http://localhost:8080/mcp"
}
}
}Load an ontology at startup using URL parameters
Open Ontosphere with a pre-loaded ontology by passing the rdfUrl parameter. You can also pass apiKey and apiKeyHeader for protected SPARQL endpoints.
http://localhost:8080/?ontology=foaf
# or load from a SPARQL endpoint:
http://localhost:8080/?rdfUrl=https://example.org/sparql&apiKey=Bearer+<token>Ontosphere Examples
Client configuration
MCP client config for connecting to a locally running Ontosphere instance via its HTTP MCP endpoint.
{
"mcpServers": {
"ontosphere": {
"url": "http://localhost:8080/mcp"
}
}
}Prompts to try
Example prompts to use with Ontosphere once connected.
- "Load the FOAF ontology and show me all the classes it defines"
- "Add a node for Alice of type foaf:Person and link her to Bob with foaf:knows"
- "Run OWL-RL reasoning on the current graph and tell me what new triples were inferred"
- "Apply the dagre-lr layout to the graph and then export it as Turtle"
- "Validate the graph against the loaded SHACL shapes and list any violations"Troubleshooting Ontosphere
MCP client cannot connect to Ontosphere
Ensure the npm dev server is running (npm run dev) and accessible at http://localhost:8080. Check that no firewall or browser extension is blocking the local port. If using a production build, run npm run build and serve the dist folder.
RDF from a SPARQL endpoint fails to load
Verify the endpoint URL is reachable from the browser. For authenticated endpoints, pass apiKey and apiKeyHeader as URL parameters (e.g., ?apiKeyHeader=Authorization&apiKey=Bearer+TOKEN). Confirm the endpoint returns a supported RDF serialization.
OWL reasoning produces no new triples
Ensure you have loaded at least one ontology with class and property axioms (e.g., rdfs:subClassOf, owl:equivalentClass). The reasoner implements OWL-RL, which requires explicit axioms in the loaded graph. Try calling loadOntology before runReasoning.
Frequently Asked Questions about Ontosphere
What is Ontosphere?
Ontosphere is a Model Context Protocol (MCP) server that browser-based rdf/ontology knowledge graph editor — load rdf from files, urls or sparql endpoints; author nodes and edges on the canvas; run owl-rl reasoning; apply multi-algorithm layout and clustering. ai-native via mcp tool surface and relay bridg It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Ontosphere?
Follow the installation instructions on the Ontosphere GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Ontosphere?
Ontosphere works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Ontosphere free to use?
Yes, Ontosphere is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Ontosphere Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Ontosphere? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Ontosphere in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Ontosphere?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.