mcpField
O
OWL-MCP

OWL-MCP

Local
ai4curation.github.ioScience & Education21Updated 73w ago
RepositoryVisit website

About OWL-MCP

OWL-MCP is an MCP server for working with Web Ontology Language (OWL) ontologies. It is aimed at researchers and semantic web users who want an AI assistant to read and edit ontologies directly. Axioms are handled as functional-syntax strings, and the ontology file on disk is kept in sync.

Key features

  1. 01Find, add and remove OWL axioms via MCP
  2. 02String-based API using OWL functional syntax
  3. 03In-memory model synced with the file on disk
  4. 04Detects file changes and notifies registered observers
  5. 05Thread-safe ontology operations
  6. 06Stored settings for frequently used ontologies

Use cases

  1. 01Letting an AI assistant create ontologies and add axioms
  2. 02Looking up human-readable labels for ontology entities
  3. 03Editing the same ontology file alongside Protege

MCP support

This is an MCP server that exposes function calls for finding, adding and removing OWL axioms to MCP clients. The documented setup uses Goose as the host.

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

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "owl": {
      "command": "uvx",
      "args": [
        "owl-mcp"
      ]
    }
  }
}
Run commanduvx owl-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiowl-mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

OWL-MCP

OWL-MCP is a Model-Context-Protocol (MCP) server for working with Web Ontology Language (OWL) ontologies.

img img

Quick Start

This walks you through using owl-mcp with Goose, but any MCP-enabled AI host will work.

Install Goose

You can use either the Desktop or CLI version of Goose from here:

Follow the instructions for setting up an LLM provider (Anthropic recommended)

Install OWL-MCP extension

You can either install directly from this link:

Or to do this manually, in the Extension section of Goose, add a new entry for owlmcp:

uvx owl-mcp

This video shows how to do this manually:

configuration

Try it out

You can ask to create an ontology, and add axioms to an ontology:

editing

How this works

The MCP server provides function calls for finding, adding, or removing OWL axioms, using OWL functional syntax. Each function call is accompanied by the file path of the OWL file on your disk. Any format supported by py-horned-owl is accepted (we following OBO guidelines and recommend functional syntax for source).

The server takes care of keeping an instance of the ontology in memory and syncing it with disk. Any CRUD operation simultaneously updates the in-memory model and syncs this with disk. If you have Protege running, Protege will also sync with local disk, and show updates.

The server is well adapted for working with OBO-style ontologies - when OWL strings are sent back to the client, labels for opaque IDs are included after #s comments, as is common for obo-format.

Key Features

  • MCP Server Integration: Connect AI assistants directly to OWL ontologies using the standardized Model-Context-Protocol
  • Thread-safe operations: All ontology operations are thread-safe, making it suitable for multi-user environments
  • File synchronization: Changes to the ontology file on disk are automatically detected and synchronized
  • Event-based notifications: Register observers to be notified of changes to the ontology
  • Simple string-based API: Work with OWL axioms as strings in functional syntax without dealing with complex object models
  • Configuration system: Store and manage settings for frequently-used ontologies
  • Label support: Access human-readable labels for entities with configurable annotation properties

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.