ComputeNexa

io.github.computenexa-gpuInfrastructure由 GitHub 账号 computenexa-gpuInfrastructure 发布v0.1.0更新于 Nov 1, 2026

Find, launch and stop private GPUs on ComputeNexa, with a quote before anything is charged.

已验证STDIO仅桌面云端与基础设施金融

概览

AI 生成的概览

让助手在 ComputeNexa 上浏览、启动、延长和停止私有 GPU 机器，并在扣费前先给出报价。

可以做什么
  • 查看 API 密钥身份、团队余额、GPU 上限与权限
  • 列出 GPU 的实时每小时价格与库存，以及可运行的软件与模型
  • 列出机器并查看单台机器的连接方式、剩余时间与费用
  • 查看消费、GPU 小时数、已完成会话与已保存项目
  • 启动、延长或自动续期机器，以及停止机器
  • 创建 Endpoint 并获取其密钥
适用场景
适合在 ComputeNexa 租用 GPU 的用户，希望助手在对话中比较价格与库存、用指定软件启动机器，或查看并停止正在运行的机器。
运行要求
通过 uvx 以 stdio 在本地运行，需要安装 uv。需要 ComputeNexa API 密钥，放在 CNX_API_KEY 中，可在控制台创建为只读或可启动停止两种权限。可选 CNX_MCP_MAX_LAUNCH_USD 限制单次调用花费（默认 25）。需要访问 ComputeNexa API 的网络。
安装前请注意
启动、延长和保持运行会从团队预付余额中扣费；服务器先返回报价，需再次确认调用，助手不应自行确认。stop_machine 无法撤销，并会删除项目之外的文件。Endpoint 密钥可访问你自己的服务器，按请求才会显示。API 密钥保存在本地设置中，不会出现在工具结果里。

安装

在 SourceWeft 中

  1. 打开 控制台中的 ComputeNexa，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

ComputeNexa MCP server

Let your AI assistant find, launch and stop private GPUs on ComputeNexa. Ask it "Which GPUs with 48 GB or more are in stock?", "Launch the cheapest one with Data Science for two hours" or "Stop it": it uses your team's API key, shows you what each launch costs, and only spends money after you agree.

Works with Claude Desktop, Claude Code, Cursor, VS Code and other assistants that support the Model Context Protocol. It runs on your computer and talks to the ComputeNexa API; your key stays in your own settings.

Set up

  1. In the ComputeNexa dashboard, open API keys and create a key:
    • Look only to browse GPUs, machines and spending;
    • Launch and stop to also launch, extend and stop machines.
  2. Install uv (it runs the server with uvx, no separate install needed).
  3. Add the server to your assistant (below), with your key as CNX_API_KEY.

Claude Code

bash
claude mcp add --env CNX_API_KEY=cnxk_... --transport stdio computenexa -- uvx computenexa-mcp

Add --scope user to use it in every project.

Claude Desktop

Settings → Developer → Edit config (claude_desktop_config.json):

json
{  "mcpServers": {    "computenexa": {      "command": "uvx",      "args": ["computenexa-mcp"],      "env": { "CNX_API_KEY": "cnxk_..." }    }  }}

Cursor

~/.cursor/mcp.json (every project) or .cursor/mcp.json (one project): the same mcpServers entry as Claude Desktop.

VS Code

.vscode/mcp.json; VS Code asks for the key once and keeps it out of the file:

json
{  "inputs": [    { "type": "promptString", "id": "cnx-key", "description": "ComputeNexa API key", "password": true }  ],  "servers": {    "computenexa": {      "type": "stdio",      "command": "uvx",      "args": ["computenexa-mcp"],      "env": { "CNX_API_KEY": "${input:cnx-key}" }    }  }}

What it can do

ToolWhat it doesKey
whoamiYour email, team, balance, GPU limit and the key's permissionsany
list_gpusGPUs with live prices and stock, cheapest first; filter by app, region, memoryany
list_appsThe apps a GPU starts with, their models, and what's installedany
list_machines · get_machineYour machines; how to connect (SSH, browser apps, API or endpoint address)any
get_usage · list_receiptsSpending and GPU-hours; finished sessions and their costany
list_projects · list_endpointsSaved projects; Endpoints and the machine each points atany
launch_machineLaunch a GPU (quote first, then launch when you agree)launch and stop
extend_machineAdd time (quote first)launch and stop
set_keep_runningRenew a machine automatically until stopped (quote first)launch and stop
stop_machineEnd a machine now; unused time is refundedlaunch and stop
create_endpoint · get_endpoint_keyA stable HTTPS address for your own server; its keylaunch and stop

A look-only key only gets the read tools (the first six rows).

Safety

  • Nothing is charged without you. launch_machine, extend_machine and set_keep_running first return a quote, e.g. "NVIDIA RTX A6000 with the datascience app for 2 h: $1.44 charged now ($0.72/h); unused time is refunded if it stops early." Only a second call with confirm=true and the quoted total goes ahead; if the price went up in between, it's refused.
  • A limit per call: a launch, extension or keep-running renewal costing more than $25 is refused. Change it with CNX_MCP_MAX_LAUNCH_USD (in dollars) in the server's env. Your team's GPU limit and prepaid balance still apply on top.
  • Your API key never appears in a tool result. Endpoint keys are shown only when you create an endpoint or ask for its key.
  • Tools that spend money or end a machine are marked as such, so your assistant asks before using them.

Settings

Variable
CNX_API_KEYRequired. A ComputeNexa API key (cnxk_…)
CNX_MCP_MAX_LAUNCH_USDMost one call may spend, in US dollars. Default 25
CNX_API_URLOnly for testing against another ComputeNexa API

Develop

bash
uv syncuv run pytestuv run ruff check src tests

Built on the ComputeNexa Python SDK and the official MCP Python SDK.

Questions: [email protected] · Security issues: see SECURITY.md.

来源：README.md，提交 d0cf599

工具

15

whoami

Who am I

Who this server's API key acts as: email, team and role, the team's balance and GPU limit, and whether the key may launch and stop machines.

无需输入参数。

list_gpus

List GPUs

GPUs with live prices (US dollars per GPU per hour) and stock, cheapest first.

输入参数appregionmin_memory_gbinclude_sold_out

list_apps

List apps

The apps a GPU can start with (basic, datascience, chat, imagegen, modelapi, voice): what each is for, the models it offers and which model we recommend per GPU memory. Give `app` for the software installed.

输入参数apppackage

list_machines

List machines

Your machines, newest first: state, GPU, app, price, time left and cost so far.

输入参数limitwhole_teamactive_only

get_machine

Get a machine

One machine: its state, how to connect (SSH command, browser apps, API or endpoint address), time left, keep-running status and costs. Never its keys.

输入参数machine_id必填

get_usage

Get usage

Spending and GPU-hours over the last N days, by GPU, app, day and project.

输入参数days

list_receipts

List receipts

Finished sessions and what each cost in the end (charged minus refunded).

输入参数dayslimit

list_projects

List projects

Saved projects (files restored into ~/work on machines launched with them) and their size.

无需输入参数。

list_endpoints

List endpoints

Endpoints: stable HTTPS addresses for your own server on a machine's port 8000, and the machine each points at now. Never their keys.

无需输入参数。

launch_machine

Launch a machine

Launch a GPU machine. Costs money: call first with confirm=false to get a quote (nothing happens), show it to the person, and only after they agree call again with the same arguments, confirm=true and expected_total_usd. The booked time is charged up front from the team's balance.

输入参数app必填gpu必填hours必填labelmodelregionconfirmprojectendpointgpu_countexpected_total_usdkeep_running_hours

extend_machine

Extend a machine

Add time to a machine at the price it launched with. Costs money: quote first (confirm=false), then confirm=true with expected_total_usd once the person agrees.

输入参数hours必填confirmmachine_id必填expected_total_usd

set_keep_running

Keep a machine running

Keep running: the machine renews itself `hours` at a time from the team's balance, at its launch price, until it's stopped. Turning it on spends money at every renewal: quote first, then confirm=true with expected_renewal_usd. Turning it off (hours=null) needs no confirmation.

输入参数hours必填confirmmachine_id必填expected_renewal_usd

stop_machine

Stop a machine

End a machine now: stopped if running, cancelled with a full refund if still starting. Files outside a project are deleted; a project is saved first. Unused time is refunded. Can't be undone.

输入参数machine_id必填

create_endpoint

Create an endpoint

A new Endpoint (owners and admins): a stable HTTPS address and key for your own server on port 8000, e.g. one per customer you serve. Launch machines for it with launch_machine(endpoint=...). Free. Its key is shown once here; get_endpoint_key shows it again.

输入参数name必填

get_endpoint_key

Get an endpoint's key

An Endpoint's key (owners and admins). Only when the person asks for it: it gives access to their server.

输入参数endpoint必填

版本历史

1
  1. v0.1.0最新Nov 1, 2026

评分

已满足适用检查项的 90%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分
  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分