cloudgpu
Rent and use a cloud GPU on CloudGPU (cloudgpu.app) through the `cloudgpu` MCP tools. Use when the user wants to rent a GPU, run a training, fine-tuning, inference or ComfyUI job on a cloud GPU, or mentions CloudGPU or cloudgpu.app, and the `cloudgpu` MCP tools are available.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 491
01 前言 Front Matter
- name
- cloudgpu
- description
- Rent and use a cloud GPU on CloudGPU (cloudgpu.app) through the `cloudgpu` MCP tools. Use when the user wants to rent a GPU, run a training, fine-tuning, inference or ComfyUI job on a cloud GPU, or mentions CloudGPU or cloudgpu.app, and the `cloudgpu` MCP tools are available.
03 SKILL.md 正文
CloudGPU
Follow these steps whenever you rent or use a GPU on CloudGPU (cloudgpu.app) through the cloudgpu MCP tools.
Before renting
- Call
get_accountandlist_gpus. Pick a GPU with enough VRAM for the job, and don't rent more GPU than the job needs. As a rough guide, LoRA on a 7–8B model fits in 24 GB, and a full fine-tune of the same model needs 80 GB or more. - Check existing
list_instancesbefore renting. A compatible running rental can run multiple approved commands inside its original limits. Optionally compare billed task costs withcompare_compute_costs, then callestimate_costwith preparation/download/output time included. - Show the user a short quote before you rent anything:
- the GPU and how many,
- the price per hour,
- the billing increment and minimum charge: some sources charge a minimum one hour and every started hour in full, with no voluntary-stop refund of unused charged time,
- the estimated hours and cost,
- the budget and time limit you will set,
- their balance after the job.
- Rent only after the user says yes. Pass
user_confirmed=trueonly in that case.
Renting
- Always set
max_spend_usdandmax_hours. CloudGPU's servers destroy the instance when either is reached, even if you have disconnected. - Keep
idle_minuteson (default 60). Include setup time when agreeing limits before creation. Never silently extend the approved budget, time or idle limits. - Call
get_statusat intervals, not in a tight loop, until the instance isrunning. - On failure, inspect actual charges and release status; do not promise zero charges or automatic refunds. Do not retry creation while the result or resource release is uncertain.
Working on the instance
- Put code and data on the instance with
upload. Do not upload credentials. - Use
run_commandfor short steps. For training, long installs or big downloads, usebackground=trueand follow progress withtail_logs. - Instances come with Python and CUDA, but not always PyTorch. Check first:
nvidia-smi -Landpython -c "import torch; print(torch.__version__, torch.cuda.is_available())". - If PyTorch is missing, plain
pip install torchinstalls a current CUDA build. It is a few GB, so run it withbackground=true. Index URLs for older CUDA versions (for example.../whl/cu124) may have no wheel for the machine's Python, which can be very new. Only use them if the project needs that CUDA version, and then create an environment with an older Python first (conda create -y -n work python=3.12, thenconda activate work && ...in each command). - If
nvidia-smishows no GPU once the instance is running, stop and tell the user. CloudGPU detects such machines and shuts them down automatically. - Do not change the root password, edit the SSH configuration, change the firewall, or stop the platform's monitoring agent (
cgpu-*processes). The platform must keep its access to the instance; if that access is lost, the platform shuts the instance down. The MCP server refuses such commands. - Never use the GPU for cryptocurrency mining or anything the acceptable use policy forbids. Instances that do so are shut down.
Finishing (always)
- Download every result: model weights, adapters, checkpoints, logs, metrics. Destroying an instance erases its disk. Workspace persists only files explicitly uploaded and ready, under its quota/retention policy. It is not an automatic disk backup. Storage fees are separate from GPU budgets.
- Call
stop_instance. - Tell the user what ran, where the results are on their computer, and the final cost from
stop_instance.
If anything goes wrong mid-way, do not leave the instance running. Download whatever exists, stop the instance, then explain what happened.
Balance and top-ups
- If
get_accountorestimate_costshows the balance would not cover the quoted job, do not callcreate_instance. Tell the user how much is missing and ask them to top up at https://cloudgpu.app/billing (card or USDT). When they say it is done, callestimate_costagain before renting. create_instancealso checks the balance. If it is below the estimate or budget plus 10%, the MCP server does not rent anything and returns an error that starts withNot rented: balance $... is below $...and points to https://cloudgpu.app/billing. If the CloudGPU API itself rejects the request with HTTP status 402, the error readsCloudGPU API error 402 <code>: <message>followed by the same billing link. Handle both the same way as above: stop, tell the user how much is missing, and do not retry.- Never top up, enter card details or move money on the user's behalf. The user does that themselves on the billing page.
Checking prices without the MCP server
If the cloudgpu tools are not available, read current prices from https://cloudgpu.app/gpu-prices.json (machine-readable, with an updated_at field) or https://cloudgpu.app/pricing. Check updated_at and tell the user how fresh the data is. Do not quote prices from memory.
Optional persistence
Discover tools and GET /v1/public/compute-capabilities first. Persistence is
unavailable when that endpoint is missing or storage is false. Never promise
free storage, a retention period or automatic output collection.
When enabled, ask before saving private project files. Use save_workspace for
regular source/config/dependency-manifest files, upload_artifact for persistent
results or datasets/models, and download_artifact to retrieve them. Pass the
saved workspace_version_id to run_job to restore the files before execution.
The service does not restore a boot disk and does not automatically save edits;
the Job command must still save its results before shutdown. Do not upload secrets.
For Jobs, prefer quote_compute for a server quote and send its quote_id with
the chosen candidate. Its required_starting_balance is separate from the task
estimate. The original estimate_cost quote belongs to create_instance.
Only need a model, not a GPU?
The same API key works for CloudGPU's model API at https://cloudgpu.app/v1. Call list_models to see the models. If you only need inference on a hosted model, use the API instead of renting a GPU.
If the MCP server is not installed
If no cloudgpu tools are available, the MCP server needs to be set up first:
- Command:
npx -y cloudgpu-mcp - Environment variable:
CLOUDGPU_API_KEY, with a key created at https://cloudgpu.app. - Never paste the key into the chat or into files in the project. Ask the user to put it in their MCP client's configuration or environment themselves.
See the README for per-client setup.
Jobs and instance reuse
Sequential approved run_command calls may reuse a running rental within its original budget, deadline and idle limit. Check ownership, readiness and free memory/disk first. Independent run_job calls and prepare_job_rerun provision separately, not into that live rental. Job/template support is configuration-specific; inspect supports_jobs and obtain a Job quote, never substitute the rental quote. Do not keep an idle GPU merely to consume a prepaid hour. Confirm result persistence and release when finished.
Connect with an approval link
In a configured MCP client, call connect_account, show the owner its link, then finish_connect after approval. No password or API key is pasted in chat. The link grants scoped access; it does not automatically install an MCP server in arbitrary AI products.
Several steps on one allocation
If installed, prepare_task_pipeline prepares up to eight reviewed sequential commands for one Job, or for run_command on an approved existing rental. It creates nothing. Commands share the filesystem and GPU but use separate shells; they do not share exported shell variables or a resident model process. Failure stops later steps. Python 3, bash and prepared dependencies are required. Review the returned command, obtain a compatible quote and explicit total budget/deadline approval, then submit one Job with a stable idempotency key. Preserve the original request on a lost response. The fingerprint is informational, not approval. Optional collection saves only pipeline-summary.json, never arbitrary results or logs; approve actual result persistence separately. Existing user instance limits and lifecycle remain unchanged.
04 同仓库更多 Skills
worktable-review-with-annotations
Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.
worktable-find-and-synthesize-context
Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.
worktable-create-or-update-docs
Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.
worktable-create-or-manage-records
Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.
worktable-create-or-manage-interactive-html
Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.
worktable-collaborate-threads
Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.