MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Agent GPU compute scheduling: compare billing, approve budgets, run tasks and persist results.
教 AI 做这类工作的 Skill,可与本项一起使用
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 29/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 8/8 | 上次检查时云端端点有响应 |
| 使用分 | 49/100 |
质量: 基础检查通过 5/5 项(仅展示,不用于排序) · 上升势头: 127 (只用于“上升中”标签)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 CloudGPU MCP。按照 https://mcp.popnx.com/i/cloudgpu-app-cloudgpu-mcp.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 5/5 项检查 · 你的提问会经过开发者的服务器(cloudgpu.app) · ✓ 命令已检查 2026年11月17日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
CustomizeConnectors
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
CloudGPU MCPhttps://cloudgpu.app/mcp在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
+ConnectorsCloudGPU MCP
用 CloudGPU MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 CloudGPU MCP,或回答中出现 CloudGPU MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
能否连接 ChatGPT 取决于方案
完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页
Plugins+Add custom MCP server
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
CloudGPU MCPhttps://cloudgpu.app/mcp开启新聊天,输入前先从插件列表中选择 CloudGPU MCP
用 CloudGPU MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 CloudGPU MCP,或回答中出现 CloudGPU MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --transport http --scope user cloudgpu https://cloudgpu.app/mcp应能看到 CloudGPU MCP 在列表中并显示已连接
用 CloudGPU MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 CloudGPU MCP,或回答中出现 CloudGPU MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor · 约 2 分钟
不需要密钥,不用安装程序
用 CloudGPU MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 CloudGPU MCP,或回答中出现 CloudGPU MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code · 约 2 分钟
不需要密钥,不用安装程序
用 CloudGPU MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 CloudGPU MCP,或回答中出现 CloudGPU MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看
通过网页连接的应用使用的地址
https://cloudgpu.app/mcpJSON 设置在下方“开发者专用”中
Claude Code
claude mcp add --transport http --scope user cloudgpu https://cloudgpu.app/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"cloudgpu": {
"url": "https://cloudgpu.app/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"cloudgpu": {
"type": "http",
"url": "https://cloudgpu.app/mcp"
}
}
}Claude Code
claude mcp add --scope user cloudgpu -- npx -y cloudgpu-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"cloudgpu": {
"command": "npx",
"args": [
"-y",
"cloudgpu-mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"cloudgpu": {
"command": "npx",
"args": [
"-y",
"cloudgpu-mcp"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"cloudgpu": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"cloudgpu-mcp"
]
}
}
}CLOUDGPU_API_KEY 机密 env说明为自动翻译,变量名保持原样;不确定时请查看原文。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
服务器要求先登录,才会列出它的工具。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月18日
注册名称已通过 GitHub 账户 cloudgpu-app 验证,该账户拥有此仓库
代码最后更新于昨天
使用 MIT
在 589 毫秒内响应(HTTP 401)
声明支持 OAuth 登录,你的 AI 应用可以带你去登录
尚未检查;我们会在检查端点时读取工具列表
尚未检查
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/cloudgpu-app-cloudgpu-mcp)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 5 项适用的基础检查中通过了 5 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于昨天,最新版本(0.16.6)于昨天进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
同一分类中有:Puter MCP, XcodeBuildMCP, Vexa, Atlassian Rovo MCP Server, Anki MCP Server
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
Connect to Atlassian Jira, Confluence, Loom, and more to search, create, and manage your work.
MCP server for Anki flashcards: adaptive review, notes, media, and deck management via AnkiConnect.
| 本项 CloudGPU MCP | Puter MCP | XcodeBuildMCP | Vexa | Atlassian Rovo MCP Server | Anki MCP Server | |
|---|---|---|---|---|---|---|
| 运行位置 | 云端或安装在电脑上都可以 | 在云端运行,无需安装 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 | 需要安装在电脑上 |
| 需要密钥 | 否 | 否 | 否 | 是 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 否 | 是 | 否 |
| 基础检查 | 5/5 | 4/4 | 3/3 | 2/4 | 4/4 | 3/3 |
| 许可证 | MIT | AGPL-3.0 | MIT | Apache-2.0 | Apache-2.0 | MIT |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
CloudGPU MCP server: let an AI agent compare GPU compute costs, approve source-specific billing, run a job, bring the results back and shut the GPU down. The same API key and balance also cover CloudGPU's OpenAI-compatible model API, so an agent can call a hosted model without renting anything.
"Fine-tune a 7B base model with LoRA on data/train.jsonl and put the adapter in ./outputs."
The agent checks live prices and quotes you, rents the GPU once you say yes, uploads your code and data, starts training in the background, watches the logs, downloads the adapter and destroys the instance. You get the files and the final cost.
It is a local (stdio) MCP server. It works with any MCP client that can start one: Codex, Claude Code, Cursor, Cline, opencode, goose, VS Code, Windsurf and others. Remote Streamable HTTP with OAuth is also available at https://cloudgpu.app/mcp; see remote MCP setup.
For the browser-approval flow, add this local MCP server without an API key first:
claude mcp add cloudgpu -- npx -y cloudgpu-mcp
For another stdio client, use command: "npx" and args: ["-y", "cloudgpu-mcp"]; omit the environment key. Ask the Agent to call connect_account, open its returned CloudGPU link yourself, approve the account, spending limit, GPU concurrency and expiry, then let it call finish_connect. Never paste your password or API key into the conversation. The client must support and configure MCP; the approval link alone does not install tools in an arbitrary assistant. Existing API-key setup remains available below.
CLOUDGPU_API_KEY.Claude Code
claude mcp add cloudgpu --env CLOUDGPU_API_KEY='<YOUR_API_KEY>' -- npx -y cloudgpu-mcp
Cursor ( ~/.cursor/mcp.json or .cursor/mcp.json )
{
"mcpServers": { "cloudgpu": { "command": "npx", "args": ["-y", "cloudgpu-mcp"], "env": { "CLOUDGPU_API_KEY": " " } } } }
</details>
Cline (MCP Servers → Configure MCP Servers → cline_mcp_settings.json )
{
"mcpServers": { "cloudgpu": { "command": "npx", "args": ["-y", "cloudgpu-mcp"], "env": { "CLOUDGPU_API_KEY": " " } } } }
</details>
opencode ( opencode.json )
{
"$schema": "https://opencode.ai/config.json", "mcp": { "cloudgpu": { "type": "local", "command": ["npx", "-y", "cloudgpu-mcp"], "environment": { "CLOUDGPU_API_KEY": " " }, "enabled": true } } }
</details>
goose ( ~/.config/goose/config.yaml , or goose configure → Add Extension → Command-line Extension)
extensions:
cloudgpu: name: cloudgpu type: stdio cmd: npx args: ["-y", "cloudgpu-mcp"] envs: CLOUDGPU_API_KEY: " " enabled: true timeout: 300
</details>
rules/cloudgpu.md into your project as AGENTS.md, .cursor/rules/cloudgpu.md or .clinerules/cloudgpu.md. It tells the agent to quote before renting, download before shutting down, and never leave a GPU running. The server also exposes the same text as the resource cloudgpu://rules.To check the install, ask your agent: "List the GPUs available, then estimate the cost for a 24 GB GPU for one hour. Do not create anything." You should see list_gpus and estimate_cost calls and a quote, and nothing is rented.
Add the local stdio server without putting a key in your command history:
codex mcp add cloudgpu -- npx -y cloudgpu-mcp
codex mcp list
In Codex, ask CloudGPU to call connect_account, open the returned link yourself, sign in, review the limits and approve, then ask it to call finish_connect. If needed, use request_top_up for an owner payment link and wait_for_funds to check the resulting balance. Never paste credentials into the conversation. Account connection does not approve paid compute; review a fresh quote and its billing terms before each allocation.
For a Codex client that supports remote MCP and OAuth, use this instead of the local entry:
codex mcp add cloudgpu --url https://cloudgpu.app/mcp
codex mcp login cloudgpu
The remote and local transports expose different tool sets; consult the current MCP documentation. Start with a read-only capability or GPU-price check and explicitly ask it not to create resources. This is direct MCP configuration, separate from the optional Codex plugin below.
The same guidance is available as two Agent Skills:
skills/cloudgpu/SKILL.md: renting and using a GPU. Claude Code loads it on demand when you ask for a GPU job. It expects the cloudgpu MCP tools to be installed (see above).skills/cloudgpu-model-api/SKILL.md: calling the OpenAI-compatible model API at https://cloudgpu.app/v1 without renting a GPU. It works with the MCP tools or with just a CLOUDGPU_API_KEY. /plugin marketplace add cloudgpu-app/cloudgpu-mcp
/plugin install cloudgpu@cloudgpu
plugin.json, mcp.json, and skills/). Codex shows it as CloudGPU. The server reads CLOUDGPU_API_KEY from the environment. codex plugin marketplace add cloudgpu-app/cloudgpu-mcp
skills/cloudgpu/ and skills/cloudgpu-model-api/ to ~/.claude/skills/.skills/cloudgpu/ and skills/cloudgpu-model-api/ to .claude/skills/ in your project. npx skills add cloudgpu-app/cloudgpu-mcp
| Tool | What it does |
|---|---|
get_account | Balance, and how many instances the account may run at once |
list_gpus | GPU models with VRAM, live price per GPU-hour and availability |
list_templates | Ready-made images: JupyterLab, Ollama, ComfyUI, LLaMA-Factory, … |
compare_compute_costs | Compare live total billed GPU cost for up to eight compatible candidates; no reservation or creation approval |
estimate_cost | Live quote for a GPU and a number of hours, plus your balance afterwards; returns a quote_id |
create_instance | Rents from an approved quote, with a budget, a time limit and an idle limit |
get_status / list_instances | Status, minutes run, cost so far, auto-shutdown limits |
run_command | Runs a command on the instance; background=true for long jobs |
tail_logs | Latest log lines, whether the job finished, GPU utilisation |
upload / download | Files and folders between your computer and the instance (SFTP) |
stop_instance | Destroys the instance and stops billing |
list_models | Models on the OpenAI-compatible API, for inference without renting a GPU |
run_job | Starts a GPU, runs one command and destroys the GPU, all on CloudGPU's servers; safe to retry with the same idempotency_key |
get_job / list_jobs | Job status, exit code, cost, the last ~4 KB of output and the job's history |
cancel_job | Stops a job and destroys its GPU |
get_agent_readiness / assess_task_fit | Anonymous capability, billing, task suitability and evidence checks; no GPU is created |
request_top_up / wait_for_funds | Human-only payment link and bounded polling for actual credit; no automatic charge or Job |
quote_storage_budget / confirm_storage_budget | Quote and explicitly approve an earmarked storage transfer; backend rollout and owner permissions apply |
resume_artifact_upload | Resume the same owned multipart reservation with the original local file and checksum |
connect_account / finish_connect | Gets a key without copying one: the user approves this assistant in the browser with a spending limit and a number of GPUs at once |
The server also provides a train_on_cloudgpu prompt.
create_instance only takes a quote_id from estimate_cost and user_confirmed=true.max_spend_usd, max_hours and an idle limit (60 minutes by default). CloudGPU's servers check them and destroy the instance when one is hit, even if your client has disconnected or your laptop is asleep.CLOUDGPU_MAX_SPEND_USD and CLOUDGPU_MAX_HOURS cap what the agent may set.stop_instance refuses until something has been downloaded, unless the user confirms force=true..ssh, .env, key files or your whole home directory needs allow_sensitive=true.run_job sends an Idempotency-Key. Resending the same job returns the same job instead of starting a second GPU, and the server refuses the same key with different parameters.connect_account has a total spending limit, a number of GPUs it may run at once and an expiry date, all enforced by CloudGPU's servers. Revoke it at https://cloudgpu.app/api and it can no longer start anything.CLOUDGPU_READ_ONLY=1 registers only the look-up tools.| Env | Default | |
|---|---|---|
CLOUDGPU_API_KEY | (or connect_account) | From https://cloudgpu.app/api. Without it, a key saved by finish_connect in ~/.config/cloudgpu/credentials.json is used |
CLOUDGPU_MAX_SPEND_USD | 50 | Highest budget the agent may set for one instance |
CLOUDGPU_MAX_HOURS | 24 | Longest time limit the agent may set |
CLOUDGPU_READ_ONLY | off | 1 = look-up tools only |
CLOUDGPU_BASE_URL | https://cloudgpu.app | Override the API host |
The key also works with the OpenAI-compatible API at https://cloudgpu.app/v1. Call list_models (or GET /v1/models) to see the available model IDs. Model prices are on cloudgpu.app/api.
These tools require persistent storage to be explicitly enabled on the server; they return storage_not_enabled until it is ready. Discover server capabilities at /v1/public/compute-capabilities. Read get_storage for current included allowance, quota, prices and retention. Storage fees are separate from GPU Job budgets. Uploads above the included allowance require accept_storage_charges=true after user agreement; the default is false. Budget-limited connect-link keys cannot enable paid storage. Files expose expires_at; downloading does not renew retention. Versions containing expired files become unavailable, while active Jobs defer deletion.
get_compute_catalog and quote_compute use public dis