広告掲載
MCP.so
ログイン

Onyx MCP Server

@MCP-Mirror

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT license

トランスポート

stdio

作者

MCP-Mirror

Onyx MCP Server について

Mirror of

#onyx#mcp-server#ai-integration

Onyx 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": {
    "lupuletic_onyx-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@lupuletic/onyx-mcp-server",
        "--client",
        "claude"
      ]
    }
  }
}

Onyx 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。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Onyx MCP Server?

Onyx MCP Server is a Model Context Protocol server that connects MCP-compatible clients to Onyx AI knowledge bases. It enables semantic search, context retrieval, and chat capabilities across your documents, acting as a bridge between MCP clients and the Onyx API.

How to use Onyx MCP Server?

Install via Smithery (npx -y @smithery/cli install @lupuletic/onyx-mcp-server --client claude) or manually by cloning the repository, installing dependencies, building, and setting the environment variables ONYX_API_TOKEN and ONYX_API_URL. Configure MCP clients (e.g., Claude Desktop, Cline) with the server command and environment variables. After setup, use the search_onyx and chat_with_onyx tools.

Key features of Onyx MCP Server

  • Enhanced semantic search with LLM relevance filtering
  • Context window retrieval (chunks above and below match)
  • Full document retrieval option
  • Chat integration using Onyx’s LLM + RAG API
  • Configurable document set filtering

Use cases of Onyx MCP Server

  • Access organizational knowledge bases through any MCP interface
  • Help customer support agents quickly find relevant information
  • Conduct deep research across company documents
  • Provide access to training materials and documentation
  • Ensure teams have the latest policies and procedures

よくある質問

1

What are the prerequisites for Onyx MCP Server?

You need Node.js v16 or higher, an Onyx instance with API access, and an Onyx API token.

2

How do I configure environment variables?

Set `ONYX_API_TOKEN` and `ONYX_API_URL` (defaults to `http://localhost:8080/api`).

3

What is the difference between the search and chat tools?

Use search for specific, targeted information with controlled context retrieval. Use chat for comprehensive answers that synthesize information from multiple sources.

4

How do I maintain conversation context across chat interactions?

After the first chat call, the response includes a `chat_session_id`. Pass this ID in subsequent calls to maintain context.

コメント

「その他」の他のコンテンツ

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K
N

Next Generation Movers: free moving quotes (remote MCP)

Next Generation Movers

Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40

Senso MCP for Joomla

sensomedia

Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea

広告掲載