Open Ontologies

general MCP Server

AI-native ontology engine: a Rust MCP server with tools for building, validating, querying, and reasoning over RDF/OWL ontologies. In-memory Oxigraph triple store, native OWL2-DL tableaux reasoner, SHACL validation, SPARQL, versioning. Single binary, no JVM.

FreshInstall Ready
generalgeneral
4 views496 stars65 forksMIT

Why This Matters

Discovered via unknown and last synced 5d ago.

FreshInstall Ready
Source
unknown
Stars
496
Last synced
5d ago
Install
Instructions detected

Install

1. Install the package

docker run -i --rm ghcr.io/fabio-rovai/open-ontologies serve

2. Add to claude_desktop_config.json

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

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)

159
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (159)

import-schema

PostgreSQL → OWL conversion

Layer

Tech

Shortcut

Action

522ms

2ms

FOAF

15

259ms

2ms

PROV-O

31

396

+0

662ms

5ms

615

+0

QUDT

99

BERTMap

0.940

621

662

Category

Tools

Contributing

[CONTRIBUTING.md](CONTRIBUTING.md)

Feature

Description

558ms

57ms

22

33

727ms

2ms

SOSA

17

SHACL

48

SIOC

17

AML

0.950

2

214

Topic

Link

Benchmarks

[docs/benchmarks.md](docs/benchmarks.md)

F1

vs o1 (paper best)

5

**11**

32

4

13ms

12ms

DOAP

22

SSN

23

206

+0

6ms

6ms

F

Fit graph to viewport (tree view)

Toppings

49

7

10

631

+4

DCAT

49

472ms

5ms

3ms

1ms

vCard

64

863ms

3ms

14ms

1,200ms

LogMap

0.76

marketplace

Browse and install 33 curated W3C/ISO/industry ontologies + open [community packs](community/README.md)

Changelog

[CHANGELOG.md](CHANGELOG.md)

R

Reset zoom (tree view)

24

24

545ms

2ms

940ms

3ms

975ms

15ms

OWL-Time

29

GeoSPARQL

15

882

+0

ADMS

8

Axioms

Open Ontologies

OLaLa

0.900

14

129

Esc

Deselect node

35

2

SKOS

5

VoID

7

256ms

5ms

796

+4

854ms

3ms

151

+0

15ms

24,490ms

Scroll

Zoom in/out

Triples

1,346

5ms

4ms

252

+55

216

+0

733ms

3ms

ODRL

31

747ms

3ms

15

**218**

Fetch

RDFS

93

118

218ms

2ms

531ms

2ms

639ms

4ms

LOCN

3

798ms

6ms

GoodRelations

43

Frontend

React 19, Vite 7, TypeScript 5.8, Tailwind CSS 4

681ms

6ms

371ms

2ms

741

+0

519ms

6ms

2ms

1ms

184ms

1ms

System

Precision

Quickstart

[docs/quickstart.md](docs/quickstart.md)

Decision

Reason

0

IES is the second-largest ontology in the marketplace by class count (after Schema.org). RDFS reasoning produces the richest inference gain of any non-general ontology — State, ClassOfEntity, and Event subclasses all generating deep transitive chains. ### Example Data Load IES example datasets directly from the official repositories: ```text onto_pull https://raw.githubusercontent.com/IES-Org/ont-ies/main/docs/examples/sample-data/event-participation.ttl onto_pull https://raw.githubusercontent.com/IES-Org/ont-ies/main/docs/examples/sample-data/hospital.ttl onto_pull https://raw.githubusercontent.com/telicent-oss/ies-examples/main/additional_examples/ship_movement.ttl ``` ### SHACL Validation ```text onto_pull https://raw.githubusercontent.com/IES-Org/ont-ies/main/docs/specification/ies-common.shacl onto_shacl ``` ### Data Mapping: EPC → IES The repo includes a sample of real UK Energy Performance Certificates ([benchmark/epc/epc-sample.csv](benchmark/epc/epc-sample.csv)) with a mapping config that transforms tabular EPC data into IES-shaped RDF: ```text onto_load benchmark/generated/ies-building-extension.ttl onto_ingest benchmark/epc/epc-sample.csv --mapping benchmark/epc/epc-ies-mapping.json onto_reason --profile rdfs ``` This mirrors NDTP's actual pipeline: CSV → IES RDF → validate → reason → query. ### IES Building Extension — Comparison with NDTP/IRIS The repo includes an [IES Building Extension](benchmark/generated/ies-building-extension.ttl) built from the UK EPC data schema and building science fundamentals, using IES 4D patterns. It was built independently — without reference to any existing implementation — then compared against the NDTP/IRIS production building ontology used in government data pipelines.

Input

macro F1

hnsw_build

Persisted HNSW indices (cosine + Poincaré) over class embeddings

Pan

--- ## Research Questions The benchmarks below are not a feature tour. Each one exists to answer a specific question, and the answers include the unflattering ones.

certify_action

Four-verdict causal certificate (EXECUTE / REJECT / EXPERIMENT / ABSTAIN); optional `causal-pywhy` feature enables backdoor identification

Route

Auth

never

liveness probe

Question

Where it is measured

Approach

Input

Classes

511

Properties

34

Metric

Before

Individuals

3

6

**60+**

Accuracy

**98.33%**

Ontology

Classes

29

0

276ms

1ms

4

0

268ms

0ms

13

0

175ms

0ms

254ms

2ms

79

118

181ms

7ms

679ms

56ms

656ms

1ms

81ms

1ms

315ms

1ms

23

70

129ms

2ms

356ms

7ms

333ms

0ms

352ms

1ms

204ms

3ms

17

38

262ms

2ms

323ms

1ms

227ms

1ms

363ms

1ms

277ms

2ms

316ms

1ms

212ms

3ms

21

13

564ms

1ms

364ms

1ms

377ms

1ms

303ms

3ms

505ms

4ms

50ms

49ms

median

p95

Matcha

0.77

Agent-OM

0.64

ALIN

0.62

LogMapLLM

0.964

LogMap-Bio

0.885

MDMapper

0.69

LogMapKG

0.917

DRAL-OA

0.830

LogMapLt

0.68

LSMatch

0.83

Configuration

Precision

206ms

3ms

Surface

Contribution is