yifanzhao2023/fan-enterprise-ontology-mcp

开发工具

本页由 AI 翻译，技术细节请以原文为准。查看原文

1 stars 0 forks 质量 79 趋势 16Apache-2.0

Repository Install

一个MCP服务器，将企业本体暴露为代理的语义记忆层。代理读取本体模式，查询命名的能力问题或原始密码，写入经过验证的实例数据,...

概览

一个MCP服务器，将企业本体暴露为代理的语义存储层。代理读取本体模式，查询命名能力问题或原始密码，编写验证实例数据，并使用离线推断的衍生事实——所有这些都是MCP工具。存储和查询层、代理集成、离线推理、SHACL验证是v1的范围。本体对齐和知识提取是计划中的，而非构建的。 - MCP（stdio） - Python（FastMCP）+ JVM 推理 CLI - Neo4j - Turtle / JSON-LD（RDF）;工具结果使用 JSON-LD 对齐的 @context - Jena 规则（OWL 2 RL + 业务规则），离线 - pySHACL（写入时 SHACL 核心，完整 SHACL 离线）- Apache 许可证 2.0 这里的企业本体是一个结构化的业务语义模型——包括类、关系、属性、约束和公理——以及符合其的实例事实。

概述（AI 翻译）

简化企业本体论。 ·让企业本体更简单

一个MCP服务器，将企业本体暴露为代理的语义存储层。

代理读取本体模式，查询命名能力问题或原始密码，编写验证实例数据，并使用离线推断的衍生事实——所有这些都是MCP工具。

语言： 英语 ·简体中文

状态： v1.0.2 — 存储、查询、代理集成、离线推理、SHACL验证以及基于映射的批处理和谱系审计均已构建和测试。知识提取是计划性的，而非构建的。

协议： MCP（标准节点）
语言： Python（MCP SDK）+ JVM 推理 CLI
存储： Neo4j
Interchange： Turtle（RDF）;工具结果使用JSON-LD对齐的@context作为业务合同层，绝不作为RDF交换格式
推理： Jena规则（OWL 2 RL + 商业规则），离线
Validation： pySHACL（写入时SHACL核心，完全离线）
Ingest： 在 Git + onto import（CLI，批处理原子）中映射伪影，每次尝试仅附加 :IngestJob 的血源行
许可证： Apache 许可证 2.0

索引

1.概述
2.目标用户与场景
3.建筑

本页由 AI 翻译，技术细节请以原文为准。

README

以下为原文 README 节选，完整内容请查看原文。

fan-enterprise-ontology-mcp

Making enterprise ontology simpler. · 让企业本体更简单

An MCP server that exposes an enterprise ontology as an agent’s semantic memory layer.

Agents read the ontology schema, query named competency questions or raw Cypher, write validated instance data, and consume offline-inferred derived facts — all as MCP tools.

Language: English · 简体中文

Status: v1.0.2 — storage, query, agent integration, offline inference, SHACL validation, and the mapping-driven batch ingest with lineage audit are all built and tested. Knowledge extraction is planned, not built.

Protocol: MCP (stdio)
Language: Python (MCP SDK) + JVM inference CLI
Storage: Neo4j
Interchange: Turtle (RDF); tool results use a JSON-LD-aligned @context as a business contract layer, never as an RDF exchange format
Inference: Jena rules (OWL 2 RL + business rules), offline
Validation: pySHACL (SHACL Core at write time, full SHACL offline)
Ingest: mapping artifacts in Git + onto import (CLI, batch-atomic), with an append-only :IngestJob lineage row per attempt
License: Apache License 2.0

1. Overview

An enterprise ontology here is a structured business semantic model — classes, relations, properties, constraints, and axioms — plus the instance facts that conform to it. Its value over a plain property graph or text index is the axioms and constraints: the model can assert that “the head of a department is necessarily the owner of that department’s work orders”, and derived facts follow from it.

This project does not build a modeling environment. It makes a human-authored ontology (in Git) usable by agents at runtime, and keeps the instance store consistent with that ontology through validation and offline inference.

TBox in Git, ABox in Neo4j. The authoritative ontology is versioned Turtle/JSON-LD. Neo4j holds instances plus two derived artifact classes. The schema an agent reads is a flat projection generated from the TBox by CI.

2. Target Users & Scenarios

在 GitHub 查看完整 README

安装

This server does not publish a one-line install command.

Open the repository installation guide 新手？先看 mcpskill.org 教程 →

配置

{
  "mcpServers": {
    "feomcp": {
      "command": "/abs/path/to/.venv/bin/feomcp",
      "args": [],
      "env": {
        "FEOMCP_ONTOLOGY_DIR": "/abs/path/to/ontology",
        "FEOMCP_NEO4J_URI": "bolt://localhost:7687",
        "FEOMCP_NEO4J_USER": "reader",
        "FEOMCP_NEO4J_PASSWORD": "…",
        "FEOMCP_NEO4J_WRITE_USER": "writer",
        "FEOMCP_NEO4J_WRITE_PASSWORD": "…"
      }
    }
  }
}