OWL-MCP

Name: OWL-MCP
Author: ai4curation

@ai4curation

Repository Homepage

About OWL-MCP

MCP server for OWL applications

#ai #mcp #semantic-web #ontology #web-ontology-language #model-context-protocol

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "owl-mcp": {
      "command": "uvx",
      "args": [
        "owl-mcp"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is OWL-MCP?

OWL‑MCP is a Model‑Context‑Protocol (MCP) server for working with Web Ontology Language (OWL) ontologies. It lets AI assistants—via any MCP‑enabled host—add, find, or remove OWL axioms stored on disk, keeping an in‑memory model in sync with the file.

How to use OWL-MCP?

Install an MCP‑enabled host such as Goose (desktop or CLI), then add OWL‑MCP as an extension using uvx owl-mcp. After configuration, you can ask the AI to create an ontology or add axioms; each operation references a local OWL file path. Any format supported by py‑horned‑owl is accepted, and OWL functional syntax is used for the API calls.

Key features of OWL-MCP

MCP integration for AI‑assisted ontology editing
Thread‑safe operations for multi‑user environments
Automatic file synchronization with disk
Event‑based notifications via registered observers
Simple string‑based API using OWL functional syntax
Configuration system for frequently‑used ontologies
Human‑readable labels for entities (OBO‑style support)

Use cases of OWL-MCP

Create a new OWL ontology entirely through natural‑language prompts
Add or remove axioms interactively while working in tools like Protégé
Maintain OBO‑style ontologies with label comments after opaque IDs
Automate ontology updates from a multi‑user AI workflow
Synchronise changes between an AI assistant and a shared OWL file on disk

FAQ from OWL-MCP

What does OWL-MCP do?

It provides MCP function calls for finding, adding, or removing OWL axioms in a local ontology file, keeping an in‑memory model synced with the disk.

What dependencies or runtime are required?

OWL‑MCP requires uvx to run and any MCP‑enabled AI host (e.g., Goose). It uses the py‑horned‑owl library under the hood to parse and write OWL files in any supported format.

Where is the ontology data stored?

The ontology data lives in a local OWL file on your disk. All CRUD operations read from and write to that file, and the server syncs the in‑memory model automatically.

Can I use OWL-MCP with Protégé?

Yes. Because the server synchronises changes to disk, Protégé—if pointed at the same file—will automatically see updates.

What syntax does OWL-MCP use for OWL axioms?

The API works with OWL axioms as strings written in OWL functional syntax, which is also the recommended source format following OBO guidelines.

Comments

More Other MCP servers

AutoBrowser MCP

autobrowser-ai

Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser

6.8K

Peekaboo MCP – lightning-fast macOS screenshots for AI agents

steipete

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

4.8K