ontology
py-ontology-server-starter
本体知识服务器启动器 — FastAPI 语义层 + Apache Jena Fuseki 三元组存储,消费者同时支持 REST 和 MCP。
用代码声明 Palantir 式对象中心本体(Object Type / Property / Link Type), 存储与查询按 W3C 标准(RDF / SPARQL 1.1)处理。应用代码只使用 SPARQL 标准, 因此即使将存储替换为 GraphDB 等,应用也无需改动。
┌─ 소비자 ──────────────────────────────┐
│ AI 에이전트(MCP) 앱·사람(REST) │
└──────────┬───────────────┬───────────┘
│ │
mcp_server.py api/rest.py ← 이중 어댑터
└───────┬───────┘
ontology/ + store/ ← 코어: 온톨로지 정의 + SPARQL 클라이언트
│
Apache Jena Fuseki (docker) ← 저장·SPARQL·추론
▲
ingest/ 파이프라인 ← 지식원 → RDF 변환·적재快速开始
# 1. 트리플스토어 기동
docker compose up -d fuseki # http://localhost:3030 (admin / admin)
# 2. 앱 설치
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
# 3. 샘플 데이터 적재 (CSV → RDF → Fuseki)
python -m ontology_server.ingest.example_csv data/sample/organizations.csv \
--object-type organization --push
# 4. REST 서버 기동
uvicorn ontology_server.main:app --reload
# → http://localhost:8000/docs
curl localhost:8000/objects/organizationRelated MCP server: mcp-ubergraph-query
MCP 适配器(面向 AI 代理)
通过 stdio 传输运行。Claude Code 项目的 .mcp.json:
{
"mcpServers": {
"ontology": {
"command": "/절대경로/.venv/bin/python",
"args": ["-m", "ontology_server.mcp_server"]
}
}
}提供的工具:list_object_types(了解模式)· search_objects(按类型查询实例)· sparql_query(只读直接查询)。
换成自己的领域
将
src/ontology_server/ontology/sample.py替换为领域本体 — 只需更改 Object Type 和 Link Type 声明,REST、MCP 和查询构建器就会随之适配。在
src/ontology_server/ingest/中添加按知识源的采集模块(参考example_csv.py)。如果需要外部对接和标准合规,将命名空间定为实际 URI 体系,并同时管理 OWL 模式文档。
测试
pytest # 단위 테스트 (Fuseki 불필요)
RUN_INTEGRATION=1 pytest # Fuseki 기동 상태에서 통합 테스트 포함配置
路径 | 作用 |
| Object/Link Type 定义框架(Palantir 式) |
| 示例本体 — 项目中需要替换的文件 |
| SPARQL 1.1 客户端(可替换存储的接入点) |
| REST 适配器 |
| MCP 适配器 |
| 知识源 → RDF 采集管道 |
| 启动 Fuseki |
许可证
MIT
Available Tools
3 toolslist_object_typesA
온톨로지에 정의된 Object Type·Link Type 전체를 반환한다. 질의 전에 먼저 호출해 스키마를 파악할 것.
Inputs: no named parameters. Returns: result
search_objectsB
지정한 Object Type의 인스턴스를 조회한다. object_type은 list_object_types의 api_name.
Inputs: object_type (required), limit. Returns: result
sparql_queryA
읽기 전용 SPARQL(SELECT/ASK/CONSTRUCT/DESCRIBE)을 직접 실행한다. 복잡한 관계 질의용.
Inputs: query (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a distinct purpose: schema discovery, instance search, and raw SPARQL querying. There is no overlap between them.
Tool names follow a consistent verb_noun pattern (list_object_types, search_objects, sparql_query). sparql_query is slightly less parallel because it uses a noun rather than a verb, but it is still clear and predictable.
Three tools is a minimal but reasonable set for an ontology server: schema listing, instance search, and flexible SPARQL access. It is on the thin side but not inadequate.
The surface covers schema discovery, instance lookup, and arbitrary read-only queries, which covers most ontology use cases. Missing write operations are likely intentional for a read-only server, so the gap is minor.
Maintenance
Related MCP Connectors
Query your own knowledge graph from any MCP client. The graph lives in a database you own.
Knowledge graph for AI agents. Query concepts, walk edges, get advisories.
Read-only search of your Sortio knowledge graph (files and entities) for Claude and ChatGPT.
Search and fetch Wikidata entities, execute SPARQL queries, and resolve external identifiers.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server that provides read-only access to Ontotext GraphDB, enabling LLMs to explore RDF graphs and execute SPARQL queries.29 npm17GPL 3.0
- AlicenseAqualityDmaintenanceEnables AI assistants to query the Ubergraph biomedical ontology SPARQL endpoint with tools for custom SPARQL queries, term lookup, search, and hierarchy traversal.4MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to interact with ontologies through the Ontology Access Kit, providing ontology querying and management capabilities.5MIT
- AlicenseAqualityCmaintenanceEnables AI assistants to query, modify, and reason over OWL/TTL/RDF ontology files using natural language, without needing SPARQL or OWL syntax.146MIT