MCP.so
ログイン

AegnticMCP MCP Server

@aegntic

基本情報

カテゴリ

その他

ライセンス

NOASSERTION

トランスポート

stdio

作者

aegntic

AegnticMCP MCP Server について

AegnticMCP automates the creation and management of MCP servers, ensuring they are stable, adaptable, and intelligent.

AegnticMCP MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "aegnticMCP": {
      "command": "docker",
      "args": [
        "run",
        "-d",
        "--name",
        "qdrant",
        "-p",
        "6333:6333",
        "-v",
        "$(pwd)/data/qdrant:/qdrant/storage",
        "qdrant/qdrant:latest"
      ]
    }
  }
}

AegnticMCP MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is AegnticMCP?

AegnticMCP is a Retrieval-Augmented Generation (RAG) system that transforms Obsidian vaults into AI-paired cognitive workflow engines with advanced Graphiti knowledge graph integration. It is built for developers and knowledge workers who want to query their Obsidian notes using Claude Code.

How to use AegnticMCP?

Install via pip (pip install obsidian-elite-rag-mcp) or from source. Run obsidian-elite-rag-cli setup and obsidian-elite-rag-cli start-databases to initialize databases, then ingest your vault with obsidian-elite-rag-cli ingest /path/to/vault. Start the MCP server with obsidian-elite-rag-cli server and configure Claude Code by adding the server entry to ~/.config/claude-code/config.json.

Key features of AegnticMCP

  • Multi-layer RAG architecture with six retrieval layers
  • Advanced Graphiti knowledge graph with 27+ entity and 40+ relationship types
  • Dual-graph architecture: Neo4j (structured) + NetworkX (unstructured backup)
  • Full MCP server implementation compatible with Claude Code
  • CLI tools for setup, ingestion, querying, and graph search
  • Real-time system status monitoring and database connection checks

Use cases of AegnticMCP

  • Ingest an entire Obsidian vault and query it using Claude Code
  • Search for entities and relationships in your knowledge graph
  • Retrieve context-rich answers combining semantic, graph, and temporal signals
  • Automate knowledge tasks like linking notes or extracting entities

よくある質問

1

What are the dependencies for AegnticMCP?

Python 3.9+, Docker & Docker Compose, an OpenAI API key, and optionally an Obsidian vault. Neo4j and Qdrant databases are handled by the setup scripts.

2

How do I install AegnticMCP?

Install from PyPI with `pip install obsidian-elite-rag-mcp` or clone the repository and run `pip install -e .` in the `obsidian-elite-rag` directory.

3

How do I connect AegnticMCP with Claude Code?

Start the MCP server using `obsidian-elite-rag-cli server`, then add a server entry to `~/.config/claude-code/config.json` with the command and environment variable `OPENAI_API_KEY`.

4

What query types does AegnticMCP support?

The CLI supports general, technical, and research queries. The MCP tools provide `query_rag`, `search_knowledge_graph`, `get_entity_context`, `get_related_entities`, and more.

5

What are the performance characteristics of AegnticMCP?

Retrieval speed under 100ms for context-rich queries, knowledge coverage over 95% recall on domain-specific queries, entity recognition accuracy above 90%, and graph traversal under 50ms up to depth 4.

コメント

「その他」の他のコンテンツ