MCPgee
MCPgee
MCPgeeMCPgee

Open Ontologies

v1.0.0•Knowledge & Memory•stable

🦀 🏠 - AI-native ontology engineering with 39 tools and 5 prompts for OWL/RDF/SPARQL.

ai-nativeclaudedescription-logicsknowledge-graphlinked-data
Share:
117
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Open Ontologies?

Open Ontologies is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🦀 🏠 - ai-native ontology engineering with 39 tools and 5 prompts for owl/rdf/sparql.

🦀 🏠 - AI-native ontology engineering with 39 tools and 5 prompts for OWL/RDF/SPARQL.

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP protocol support

Use Cases

Build and manage OWL/RDF ontologies and knowledge graphs using AI.
Query SPARQL endpoints and work with linked data structures.
Leverage 39 tools and AI-native ontology engineering techniques for knowledge representation.
fabio-rovai

Maintainer

LicenseMIT License
Languagerust
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx open-ontologies

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Open Ontologies

Open Ontologies is an AI-native ontology engineering MCP server built in Rust that gives AI assistants over 70 tools for creating, loading, validating, querying, and reasoning over OWL/RDF knowledge graphs. It ships as a single binary backed by an in-memory Oxigraph triple store with SPARQL 1.1 support and OWL2-DL reasoning. Knowledge engineers, data architects, and AI researchers use it to build domain ontologies, align datasets, execute SPARQL queries, and apply description logic reasoning — all through natural language prompts.

Prerequisites

  • The open-ontologies binary: download a pre-built release from GitHub, run via Docker, or build from source with Rust 1.85+
  • An MCP-compatible client such as Claude Desktop, Claude Code, Cursor, or Windsurf
  • Optional: Node.js 18+ and Rust/Cargo if building the desktop Studio UI
1

Install the open-ontologies binary

Download the pre-built binary for your platform from the GitHub releases page, or pull the Docker image for a zero-install option.

# macOS (Apple Silicon) — pre-built binary
curl -LO https://github.com/fabio-rovai/open-ontologies/releases/latest/download/open-ontologies-aarch64-apple-darwin
chmod +x open-ontologies-aarch64-apple-darwin
mv open-ontologies-aarch64-apple-darwin /usr/local/bin/open-ontologies

# Docker
docker pull ghcr.io/fabio-rovai/open-ontologies:latest

# From source (requires Rust 1.85+)
git clone https://github.com/fabio-rovai/open-ontologies.git
cd open-ontologies && cargo build --release
2

Initialise local state

Run the `init` subcommand to create the local state directory and default configuration.

open-ontologies init
3

Add to your MCP client configuration

Register the server using the `serve` subcommand. No environment variables are required — all configuration is done through the binary and MCP client settings.

# For Claude Code
claude mcp add open-ontologies -- /usr/local/bin/open-ontologies serve
4

Optional: install marketplace ontologies

Open Ontologies includes a marketplace with 32 pre-indexed ontologies from W3C, ISO, and industry standards. Install them directly through the AI tool.

# These commands are available as MCP tool calls:
# onto_marketplace install ies-core
# onto_marketplace install schema-org
5

Optional: build and run the desktop Studio UI

The project includes a Tauri-based desktop app with a visual ontology editor, AI chat panel, and lineage audit trail.

cd studio && npm install
PATH=/opt/homebrew/bin:~/.cargo/bin:$PATH npm run tauri dev

Open Ontologies Examples

Client configuration (Claude Desktop)

Point Claude Desktop at the locally installed open-ontologies binary. Use the Docker variant if you prefer not to install the binary directly.

{
  "mcpServers": {
    "open-ontologies": {
      "command": "/usr/local/bin/open-ontologies",
      "args": ["serve"]
    }
  }
}

// Docker alternative:
// {
//   "mcpServers": {
//     "open-ontologies": {
//       "command": "docker",
//       "args": ["run", "-i", "--rm", "ghcr.io/fabio-rovai/open-ontologies", "serve"]
//     }
//   }
// }

Prompts to try

Open Ontologies supports rich ontology engineering workflows through natural language. The /sketch and /build commands trigger structured multi-step build sequences.

- "Build me a Pizza ontology following the Manchester University tutorial with all toppings and defined classes."
- "Load the schema.org ontology and run SPARQL to find all subclasses of schema:Person."
- "Validate my ontology for OWL2-DL consistency and explain any violations."
- "Align my product ontology with schema.org using fuzzy matching."
- "Run OWL-RL reasoning over the loaded ontology and report new inferences."
- "/sketch a domain ontology for a hospital patient management system."

Troubleshooting Open Ontologies

Binary fails to start or gives a 'killed' error on macOS

macOS may quarantine unsigned binaries. Run `xattr -d com.apple.quarantine /usr/local/bin/open-ontologies` to remove the quarantine flag, then retry.

SPARQL queries return empty results after loading an ontology

Confirm the ontology loaded successfully by calling the `onto_stats` tool. If the triple count is 0, the RDF/OWL file may have a parsing error — run `onto_validate` to check for syntax issues.

Reasoning takes a very long time on large ontologies

Large OWL2-DL ontologies can require significant compute. Use `--profile rdfs` for lighter reasoning that applies only RDFS entailment rules, which is much faster for exploratory work.

Frequently Asked Questions about Open Ontologies

What is Open Ontologies?

Open Ontologies is a Model Context Protocol (MCP) server that 🦀 🏠 - ai-native ontology engineering with 39 tools and 5 prompts for owl/rdf/sparql. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Open Ontologies?

Follow the installation instructions on the Open Ontologies GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Open Ontologies?

Open Ontologies works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Open Ontologies free to use?

Yes, Open Ontologies is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Open Ontologies Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to Open Ontologies? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.

MemPalace

★ 52.6k

A 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

★ 15.4k

An 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

★ 13.7k

Memory for 24/7 proactive agents like OpenClaw.

MemOS

★ 9.3k

MemOS (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

★ 5.4k

Build, 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.

Knowledge & MemoryBrowse All Servers

Quick Config Preview

{ "mcpServers": { "open-ontologies": { "command": "npx", "args": ["-y", "open-ontologies"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Open Ontologies?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides