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.
Discovered via unknown and last synced 5d ago.
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)
PostgreSQL → OWL conversion
Tech
Action
2ms
15
2ms
31
+0
5ms
+0
99
0.940
662
Tools
[CONTRIBUTING.md](CONTRIBUTING.md)
Description
57ms
33
2ms
17
48
17
0.950
214
Link
[docs/benchmarks.md](docs/benchmarks.md)
vs o1 (paper best)
**11**
4
12ms
22
23
+0
6ms
Fit graph to viewport (tree view)
49
10
+4
49
5ms
1ms
64
3ms
1,200ms
0.76
Browse and install 33 curated W3C/ISO/industry ontologies + open [community packs](community/README.md)
[CHANGELOG.md](CHANGELOG.md)
Reset zoom (tree view)
24
2ms
3ms
15ms
29
15
+0
8
Open Ontologies
0.900
129
Deselect node
2
5
7
5ms
+4
3ms
+0
24,490ms
Zoom in/out
1,346
4ms
+55
+0
3ms
31
3ms
**218**
RDFS
118
2ms
2ms
4ms
3
6ms
43
React 19, Vite 7, TypeScript 5.8, Tailwind CSS 4
6ms
2ms
+0
6ms
1ms
1ms
Precision
[docs/quickstart.md](docs/quickstart.md)
Reason
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.
macro F1
Persisted HNSW indices (cosine + Poincaré) over class embeddings
--- ## 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.
Four-verdict causal certificate (EXECUTE / REJECT / EXPERIMENT / ABSTAIN); optional `causal-pywhy` feature enables backdoor identification
Auth
liveness probe
Where it is measured
Input
511
34
Before
3
**60+**
**98.33%**
Classes
0
1ms
0
0ms
0
0ms
2ms
118
7ms
56ms
1ms
1ms
1ms
70
2ms
7ms
0ms
1ms
3ms
38
2ms
1ms
1ms
1ms
2ms
1ms
3ms
13
1ms
1ms
1ms
3ms
4ms
49ms
p95
0.77
0.64
0.62
0.964
0.885
0.69
0.917
0.830
0.68
0.83
Precision
3ms
Contribution is