Skip to main content
Glama
anils123
by anils123

製造トレーサビリティ・インテリジェンス・プラットフォーム

Neo4j、Amazon Bedrock、MCP を使用した、製造トレーサビリティのための GraphRAG 搭載エージェント型 AI プラットフォーム。

アーキテクチャ

┌─────────────────────────────────────────────────────────────────────┐
│                    INGESTION & ENRICHMENT LAYER                      │
│  Connectors → Chunking → Embeddings → Entity Extraction →           │
│  Entity Resolution → Graph Construction                              │
└──────────────────────────┬──────────────────────────────────────────┘
                           │
┌──────────────────────────▼──────────────────────────────────────────┐
│                    KNOWLEDGE GRAPH (Neo4j)                           │
│  Product → Requirement → Component → TestCase → TestRun →           │
│  Defect → ChangeRequest                                              │
└──────────────────────────┬──────────────────────────────────────────┘
                           │
┌──────────────────────────▼──────────────────────────────────────────┐
│                    RETRIEVAL LAYER                                   │
│  VectorRetriever │ GraphRAGRetriever │ NL2CypherRetriever │ Hybrid  │
└──────────────────────────┬──────────────────────────────────────────┘
                           │
┌──────────────────────────▼──────────────────────────────────────────┐
│                    AGENT LAYER                                       │
│  LangGraph Agent (plan→retrieve→reason→validate→respond)            │
│  Strands Agent (tool-calling with 5 specialized graph tools)        │
└──────────────────────────┬──────────────────────────────────────────┘
                           │
┌──────────────────────────▼──────────────────────────────────────────┐
│                    INTERFACE LAYER                                   │
│  FastAPI REST │ MCP Server (Claude Desktop / Cursor compatible)     │
└─────────────────────────────────────────────────────────────────────┘

Related MCP server: Knowledge Graph MCP Server

クイックスタート

1. 前提条件

  • Neo4j 5.x(APOC プラグイン付き)

  • Python 3.11+

  • Bedrock アクセス権限を持つ AWS 認証情報(Claude 3.5 Sonnet + Titan Embed v2)

2. セットアップ

cd manufacturing-graphrag
python -m venv .venv
.venv\Scripts\activate          # Windows
pip install -r requirements.txt
python -m spacy download en_core_web_sm
copy .env.example .env          # Edit with your credentials

3. Neo4j の起動(Docker)

docker-compose up neo4j -d

4. ナレッジグラフのシード

set PYTHONPATH=src
python scripts/seed_data.py

5. プラットフォームの起動

# API server
python main.py api

# MCP server (for Claude Desktop)
python main.py mcp

# Both
python main.py all

6. ドキュメントの取り込み

python scripts/ingest.py path/to/spec.pdf path/to/requirements.csv

API エンドポイント

メソッド

エンドポイント

説明

GET

/health

ヘルスチェック

GET

/graph/stats

ラベル別ノード数

POST

/ingest/file

ドキュメントのアップロードと取り込み

POST

/ingest/record

構造化 API レコードの取り込み

POST

/query

ハイブリッド GraphRAG クエリ

POST

/agent/langgraph

LangGraph 推論エージェント

POST

/agent/strands

Strands ツール呼び出しエージェント

GET

/traceability/defect/{id}

完全な欠陥トレーサビリティチェーン

GET

/traceability/product/{id}

製品トレーサビリティの概要

クエリ例

# Hybrid GraphRAG query
curl -X POST http://localhost:8000/query \
  -H "Content-Type: application/json" \
  -d '{"question": "What components are affected by the thermal runaway defect?"}'

# LangGraph agent — multi-step reasoning
curl -X POST http://localhost:8000/agent/langgraph \
  -d '{"question": "Trace the full impact chain of DEF-001 and identify all change requests needed"}'

# Strands agent — tool-calling
curl -X POST http://localhost:8000/agent/strands \
  -d '{"question": "Which critical defects are blocking the EV BMS release?"}'

# Defect traceability
curl http://localhost:8000/traceability/defect/DEF-002

MCP 統合(Claude Desktop)

config/claude_desktop_mcp.json の内容を Claude Desktop の claude_desktop_config.json にコピーします。

利用可能な MCP ツール:

  • ask_manufacturing_ai — ハイブリッド GraphRAG Q&A

  • semantic_search — ベクトル類似度検索

  • graph_trace — グラフ走査による検索

  • natural_language_to_cypher — NL2Cypher

  • get_defect_chain — 完全な欠陥トレーサビリティ

  • get_requirement_traceability — 要件カバレッジ

  • product_health_dashboard — 製品メトリクス

ナレッジグラフのスキーマ

(Product)-[:HAS_REQUIREMENT]->(Requirement)
(Component)-[:IMPLEMENTS]->(Requirement)
(TestCase)-[:VALIDATES]->(Requirement)
(TestRun)-[:INSTANCE_OF]->(TestCase)
(TestRun)-[:FOUND_IN]->(Defect)
(Defect)-[:AFFECTS]->(Component)
(Defect)-[:TRIGGERS_CHANGE]->(ChangeRequest)
(ChangeRequest)-[:MODIFIES]->(Component)
(Document)-[:CONTAINS_CHUNK]->(Chunk)
(Chunk)-[:MENTIONS]->(any entity)

テストの実行

set PYTHONPATH=src
pytest tests/ -v
F
license - not found
Not graded
quality - not tested
C
maintenance

Maintenance

0Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • F
    license
    Not graded
    quality
    D
    maintenance
    Enables storage and retrieval of knowledge in a graph database format, allowing users to create, update, search, and delete entities and relationships in a Neo4j-powered knowledge graph through natural language.
    5
  • F
    license
    Not graded
    quality
    D
    maintenance
    Enables enterprise document retrieval using graph-based reasoning and knowledge graphs. Allows agents to search and extract information from scattered documents through structured entity and relationship extraction.
    2
  • F
    license
    C
    quality
    D
    maintenance
    Combines a knowledge graph with RAG (Retrieval-Augmented Generation) capabilities for semantic code indexing and search. Enables creating entity relationships, managing observations, and performing semantic searches across indexed codebases.
    13

View all related MCP servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/anils123/manufacturing-graphrag'

If you have feedback or need assistance with the MCP directory API, please join our Discord server