Is Novita MCP Server fully released?
No. It is currently in beta and only supports GPU instance management. Additional resource types will be added in future releases.
@novitalabs
基本信息
The Model Context Protocol (MCP) server that provides seamless interaction with Novita AI platform resources
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"@novitalabs/novita-mcp-server": {
"command": "npx",
"args": [
"-y",
"@novitalabs/novita-mcp-server"
],
"env": {
"NOVITA_API_KEY": ""
}
}
}
}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。
Novita MCP Server is a Model Context Protocol server that enables seamless interaction with Novita AI platform resources. It is currently in beta and exclusively supports management of GPU instances. This server is intended for users of compatible MCP clients such as Claude Desktop, Cursor, or any other MCP-compatible client.
Install the package globally via npm (npm install -g @novitalabs/novita-mcp-server) or using Smithery. Obtain a Novita API key from the Novita AI Key Management page. Then configure the server in your MCP client (Claude Desktop or Cursor) by adding a JSON entry with the command npx -y @novitalabs/novita-mcp-server and the environment variable NOVITA_API_KEY.
No. It is currently in beta and only supports GPU instance management. Additional resource types will be added in future releases.
You need a Novita API key (obtainable from the Novita AI console) and a compatible MCP client such as Claude Desktop or Cursor.
Add the following to your MCP client configuration: `"command": "npx", "args": ["-y", "@novitalabs/novita-mcp-server"], "env": { "NOVITA_API_KEY": "your_api_key_here" }`.
The README explicitly recommends Claude Desktop and Cursor but also mentions any other compatible MCP client.
The API key is passed as an environment variable (`NOVITA_API_KEY`) in the MCP client configuration; no other authentication or transport details are documented.
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,

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
Painless E2E Automation for Mobile and Web

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
Hindsight: Agent Memory That Learns
评论