All servers / Cloud / CloudGPU MCP server
CloudGPU MCP server
MCP server and command-line tool for cloudgpu.app: let Claude Code, Cursor, Cline, opencode, goose and other MCP clients (or you, from a terminal) rent a GPU wi
Tested by ConnectATDScore 84 out of 100. Tested 2026-11-18 on package version 0.16.6. Package: cloudgpu-mcp · source
Score breakdown
| Runs | 18 / 20 | |
|---|---|---|
| Tool descriptions | 14 / 20 | |
| Package safety | 20 / 20 | |
| Maintenance | 20 / 20 | |
| Adoption | 12 / 20 |
What we saw
- Starts and answers the MCP handshake: yes (2.2 seconds including download)
- Tools offered: 59
- Last published: 2026-11-17
- Weekly downloads (npm): 3,462
- License: MIT · Direct dependencies: 3
Want this server set up for your team?
ConnectATD builds AI automation and wires up MCP servers like this one. Tell us what you are trying to do.
Talk to ConnectATDTools and how they are described
Agents choose tools from these descriptions. Under each name you can see how many of its parameters are explained.
request_top_up0 of 1 parameter describedCreates a short-lived link only. No checkout, card charge or transfer is made. Show the link to the human owner; never complete payment for them. Payment completion does not approve a GPU quote.
wait_for_funds0 of 2 parameters describedRead-only polling of actual account balance and real-top-up signal for up to 60 seconds. No payment, job submission or authorization. If still pending, return to the owner; do not blindly repeat rentals.
get_agent_readinessno parametersNo login or spending: capabilities, source-specific billing, task prerequisites, limitations, recent aggregate Job evidence and known issues. Unknown data is not a healthy or verified result.
assess_task_fit0 of 6 parameters describedRead-only task suitability before quoting a GPU. Returns blockers, unverified requirements and evidence status; does not benchmark, approve spending or guarantee availability.
list_rental_regions0 of 1 parameter describedRead-only qualified continent catalog shared with the rental UI. Use enabled and inventory/capability/count constraints. Request estimate_cost with the same continent before renting. Countries and individual datacenters are not selectable. Empty inventory does not authorize renting in another continent.
list_regional_offers0 of 7 parameters describedAnonymous, read-only native regional stock observations, independent price evidence ages, billing references and known/unknown limits. Supply the human owner's country explicitly; the Agent server IP is not its owner's location. Counts are not reservations or verified single-host multi-GPU allocations. Published SKU references are not region-bound executable quotes; these observations are not executable quotes. Use list_rental_regions and estimate_cost for enabled continent-constrained rentals; exact countries/datacenters are unsupported. Unsupported, stale or failed observations do not prove global stockout. Follow has_more/next_after_id; pagination is a live view, not a frozen snapshot.
list_task_templatesno parametersPublic, local and read-only. Inspect small task recipes and requirements before quoting. Does not call an API, rent a GPU, install dependencies or reserve capacity.
prepare_task_template0 of 18 parameters describedLocal preparation only. Returns a command and optional Workspace/output fields; never submits or spends money. Quote, explicit GPU/budget/time approval and existing storage consent are still required by run_job. No guaranteed application compatibility or automatic retry.
compare_compute_costs0 of 5 parameters describedRead-only live quote comparison for up to eight explicit compatible GPU candidates. Accounts for minimum one-hour versus per-minute billing. No capacity reservation, GPU creation, benchmark, automatic selection or approval. Run estimate_cost for the selected rental afterward.
prepare_task_pipeline0 of 3 parameters describedLocal read-only preparation of 1–8 reviewed commands for one bounded Job or an approved existing rental. Reuses GPU and disk across steps; stops on the first error. Does not create, retry, install dependencies, approve spending or change an instance lifecycle. Summary persistence is optional and never implies paid-storage consent.
get_job_batch_receipt0 of 1 parameter describedRead only saved accepted Job IDs and uncertain submission intents for the original batch key, API key and endpoint. No API request or GPU creation. Local state is historical, not live release evidence; a missing entry does not prove non-creation. Commands, tokens and signed URLs are never stored.
prepare_job_batch0 of 3 parameters describedLocal, read-only preparation for up to eight Jobs with fresh per-Job quotes and one aggregate cap. No API requests, reservations, installations or automatic execution retries. Retain the immutable plan hash and batch key.
get_job_batch0 of 1 parameter describedRead-only status and cost summary for explicit Job IDs. Does not retry, cancel, create or claim independent supplier release verification.
get_server_job_batch0 of 1 parameter describedRead persisted child Job states and costs after either client or server restarts. Does not create or retry resources.
run_server_job_batch0 of 5 parameters describedPaid. Use the exact reviewed prepare_job_batch manifest/hash. Enqueue is atomic and persists on the server; each Job reserves its own budget and waits for account/key concurrency. No automatic command retries and no partial client-side fallback. Whole-hour Jobs require a separate accepted current billing quote per allocation.
cancel_server_job_batch0 of 2 parameters describedCancel queued children without starting a GPU; request safe shutdown of active children. Preserve outputs first. Previously started whole-hour charges remain payable.
run_job_batch0 of 5 parameters describedPaid: submit an explicitly approved immutable manifest using existing durable Jobs, each with a quote, budget and deadline. Aggregate worst-case budget is capped. Partial success is possible. On lost responses replay the IDENTICAL manifest/key; never create replacement GPUs or retry failed execution automatically. Persist the returned receipt. No transaction rollback or independent batch scheduler.
get_storageno parametersStorage availability, used bytes, reserved uploads and account quota. No money is spent.
list_filesno parametersPersistent artifacts, model/data files and Workspace files. Availability depends on storage being enabled.
list_workspacesno parametersSaved project Workspaces; versions are immutable file manifests.
list_workspace_versions0 of 1 parameter describedList saved immutable versions of an owned Workspace.
get_workspace_version0 of 1 parameter describedRead the path-to-file manifest for an owned version.
list_workspace_instancesno parametersLists your running GPUs that this key may access. Budgeted Agent keys only see instances created by the same key.
get_workspace_application0 of 2 parameters describedCheck file restoration on an existing GPU. This does not create, stop or restart a GPU. An uncertain result must be checked, never automatically resubmitted.
quote_storage_budget0 of 2 parameters describedQuote reserving GPU wallet funds for persistent storage, or returning unused surplus. No transfer yet. Shows USD rate, budget-based capacity and 30-day file expiry. Budget-limited keys cannot move funds; ask owner to use Web or unrestricted key.
confirm_storage_budget0 of 2 parameters describedMoves wallet funds only after the user approves the exact quote. Retrying the same quote cannot transfer twice. Reservation is not billed usage; daily actual peak consumes the budget. Never approve automatically.
resume_artifact_upload0 of 3 parameters describedResume the same unexpired multipart reservation. Requires the original SHA-256 reported when upload paused. Skips completed parts; renews expiring URLs. Never mixes changed files or creates another reservation.
apply_workspace0 of 3 parameters describedRestore project files to a new private directory on your existing running GPU. Does not install dependencies, execute code, overwrite existing files, rent, restart or stop a GPU. GPU rental billing continues; transfer consumes its network and disk. Ask the user before applying. Repeat requests for the same version and instance return the existing result; failures require inspection, not automatic retries.
delete_workspace_version0 of 2 parameters describedDeletes a saved version, releasing its file references. Refuses versions pinned by active Jobs. Ask the user first.
upload_artifact1 of 3 parameters describedUploads a local regular file in resumable-sized parts. Consumes storage quota; retention and pricing depend on the account policy. Credential files are refused.
download_artifact0 of 2 parameters describedStreams a persistent file to this computer. Never overwrites an existing local file.
save_workspace1 of 4 parameters describedSaves 1–100 regular project files as an immutable version. Refuses secrets and symlinks; skips .git, node_modules, __pycache__ and .venv. Save dependency manifests, not the operating system. Pass the returned workspace_version_id to run_job.
delete_file0 of 2 parameters describedPermanently deletes a persistent file or cancels an unfinished upload. Files pinned by a Workspace version cannot be deleted.
diagnose_job0 of 1 parameter describedRead-only Job diagnosis and observed platform instance state. Never creates, stops or retries a GPU. Does not claim supplier release verification or classify every command failure as user error.
save_job_output0 of 3 parameters describedWith approval, persist the ended Job log tail as a small Artifact using existing storage quota and retention. This is not the full log or binary output collection. Refuses recognizable credentials, quoted/aliased fields and bounded escaped representations or queried URLs. This is not a guarantee that arbitrary logs contain no secrets; save only logs you know are sanitized. Never touches GPU resources. Reuses a matching verified snapshot when found; cross-client concurrent calls may create duplicates.
get_compute_catalogno parametersGPU catalog, templates and billing without an API key. Does not rent anything.
quote_compute0 of 7 parameters describedFive-minute server quote: separates estimated task cost from required starting balance and marks supports_jobs. No GPU is started. Pass its quote_id to run_job.
get_accountno parametersBalance in USD, how many instances this account may run at once, and how many are running now.
list_gpus2 of 2 parameters describedGPU catalog with per-card VRAM, live starting price in USD, availability, and native configurations (GPU count, CPU, RAM, disks, region, interconnect and whole-instance price) when provided. Unavailable models remain discoverable. Request an exact quote before renting.
list_templatesno parametersReady-made instance images (e.g. JupyterLab, Ollama, ComfyUI, LLaMA-Factory) with the GPU each recommends. Templates with has_api_endpoint get a public HTTPS api_url.
estimate_cost4 of 5 parameters describedLive price and estimated cost for a GPU, plus your balance after it. Returns a quote_id that create_instance needs. Show the quote to the user and get an explicit yes before renting.
list_modelsno parametersModels on CloudGPU's OpenAI-compatible API (same key, same balance). Use them from code with base_url https://cloudgpu.app/v1 instead of renting a GPU when you only need inference.
connect_account3 of 4 parameters describedUse when there is no API key. Starts an approval request and returns a link. The user opens it, signs in to cloudgpu.app and approves this assistant with a spending limit and a maximum number of GPUs at once; CloudGPU's servers enforce both. Then call finish_connect. No money is spent.
finish_connectno parametersAfter the user approved the link from connect_account: waits up to about a minute for the approval, then stores the new key on this computer (~/.config/cloudgpu/credentials.json, readable only by the user) and uses it from now on. The key itself is never shown.
get_job0 of 1 parameter describedStatus of a job (queued / provisioning / running / stopping / succeeded / failed / cancelled / needs_attention), exit code, cost so far, the last ~4 KB of the command's output and the job's event history.
list_jobs0 of 1 parameter describedRecent jobs on this account with status and cost.
get_status0 of 1 parameter describedStatus (creating / running / stopped / failed), minutes run, cost so far, whether SSH is ready, the public api_url if the template has one, and the auto-shutdown limits.
list_instancesno parametersInstances on this account: running, starting, and those stopped in the last 7 days, with cost.
create_instance5 of 6 parameters describedRents the GPU from a quote. Costs money. Requires a quote_id from estimate_cost that the user has approved. max_spend_usd and max_hours are enforced by CloudGPU's servers: the instance is destroyed when either is reached, even if this assistant has disconnected. idle_minutes destroys it after the GPU sits idle that long (installing packages and downloading data count as idle, so allow for setup). setup_script (optional bash) runs once as root after the instance is handed over; its output is in /root/cloudgpu-setup.log.
resolve_model_reference0 of 4 parameters describedRead-only. Resolve a public Hugging Face model revision and explicit file list to immutable commit, sizes and available LFS SHA-256 checksums. Does not download weights, rent a GPU or authenticate to Hugging Face. Review model license and application compatibility separately.
prepare_model_deployment0 of 2 parameters describedPreparation only; no GPU is started. Create a reviewed setup script for the existing ComfyUI template. Downloads go from the public model host directly to the rented GPU, never through CloudGPU storage. Use model names as categories (checkpoints, loras, vae, diffusion_models, text_encoders, clip, controlnet, upscale_models). Does not install custom nodes, execute workflows, accept licenses for the user, or promise compatibility. Pass the setup_script only after explicit approval to the existing deployment flow.
prepare_job_rerun0 of 1 parameter describedRead-only. Retrieve the original command, pinned model references and Workspace without starting anything. Request a fresh quote, check Workspace expiry and obtain explicit budget approval before calling run_job with a NEW idempotency key. Never reuse the old quote or key.
run_job14 of 15 parameters describedCosts money. CloudGPU starts a GPU, runs one bash command on it, then destroys the GPU, all on its servers, so it finishes even if this assistant disconnects. max_spend_usd and max_hours are enforced by the servers. Retrying with the same idempotency_key never starts a second GPU; this tool generates one if you leave it out and returns it. The disk is erased when the job ends. When automatic_output_collection is available, declare outputs and write only those files under $CLOUDGPU_OUTPUT_DIR for persistent storage before release. Otherwise upload results yourself or print them. Storage retention and fees follow the account policy; collection consumes the same GPU budget and may fail. Requires the user's explicit yes on the GPU, budget and time limit.
cancel_job0 of 1 parameter describedStops a job: if a GPU was started it is destroyed and billing stops. Output not yet uploaded by the command is lost.
run_command3 of 5 parameters describedRuns a bash command on the instance as root, in an interactive-style shell so conda/venv from ~/.bashrc are active. Foreground returns the exit code and the last 20k characters of output. For anything longer than a few minutes (training, big downloads) use background=true, then tail_logs.
upload1 of 4 parameters describedCopies a local file or directory (this computer) to the instance over SFTP. node_modules, .git and __pycache__ are skipped. Credentials files (.ssh, .env, keys) are refused unless allow_sensitive is true and the user asked for it.
download1 of 3 parameters describedCopies a file or directory from the instance to this computer. Do this for every result before stop_instance: destroying an instance erases its disk.
tail_logs0 of 4 parameters describedLast lines of a background job's log (job_id) or any log file (path), whether the job is still running and its exit code, plus current GPU utilisation and memory.
stop_instance0 of 2 parameters describedDestroys the instance and stops billing. Its disk is erased. If commands were run on it in this session and nothing was downloaded, this refuses unless force=true (only after the user confirms the results are not needed).
Tested in a sandbox with an empty environment: no API keys, a throwaway folder, nothing from a real account. A passing test shows the server runs and responds. It is not a security audit.