What prerequisites are needed to run Onyx MCP Server?
You need Node.js v16 or higher, an Onyx instance with API access, and an Onyx API token.
@lupuletic
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"onyx-mcp-server": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@lupuletic/onyx-mcp-server",
"--client",
"claude"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
A Model Context Protocol (MCP) server that connects any MCP-compatible client to an Onyx AI knowledge base, enabling semantic search and chat capabilities across your documents.
Install via npm or Smithery, configure environment variables ONYX_API_TOKEN and ONYX_API_URL, then add the server configuration to your MCP client (e.g., Claude Desktop or Cline). Once configured, use the search_onyx tool for targeted document search or the chat_with_onyx tool for comprehensive LLM + RAG answers.
You need Node.js v16 or higher, an Onyx instance with API access, and an Onyx API token.
Add a server entry to `~/Library/Application Support/Claude/claude_desktop_config.json` with the command `node`, the path to `build/index.js`, and environment variables `ONYX_API_TOKEN` and `ONYX_API_URL`.
It provides two tools: `search_onyx` for semantic search with configurable context retrieval, and `chat_with_onyx` for comprehensive LLM + RAG answers with optional chat session persistence.
Use Search when you need specific, targeted information and want to control how much context is retrieved. Use Chat when you need comprehensive answers that synthesize information from multiple sources.
`ONYX_API_TOKEN` (your API token) and `ONYX_API_URL` (the URL of your Onyx API, e.g., `http://localhost:8080/api`).
不止于 CSS

Model Context Protocol Servers
🚀 The fast, Pythonic way to build MCP servers and clients.

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w
Open-source MCP to use Blender with any LLM
评论