CloudGPU MCP
NPM · CLOUDGPU-MCP · 2 COMPONENTS
Agent GPU compute scheduling: compare billing, approve budgets, run tasks and persist results.
Available components
Last scanned (10 hours ago)
Scores higher than 40% of npm servers
Category Cloud Infrastructure
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security48
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 34 of 99 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to cloudgpu-app/cloudgpu-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 0 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability78
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 5957 tokens (~97/item across 61 items; 60 tools + 1 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management30
- Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage74
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 22% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 62 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (15)
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Malware scan in Supply Chain SecurityMalware scan not yet available for this package.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Nov 26 +11
- Malware scan: unverified → pass ▲ security
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → 0.84 ▲ functional
- Dependency health: unverified → 0.83 ▲ functional
- Package version: 0.16.7 → 0.16.8 functional
- 20 Nov 26 −25
- Malware scan: pass → unverified ▼ security
- Known CVEs: pass → unverified ▼ security
- Dependency health: 0.83 → unverified ▼ functional
- Package version: 0.16.6 → 0.16.7 functional
- 19 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Nov 26 +26
- CVE-2023-54404 no longer affects this package ▲ security
- Malware scan: unverified → pass ▲ security
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → 0.84 ▲ functional
- 17 Nov 26 −20
- Known CVEs: fail → unverified ▼ security
- Malware scan: pass → unverified ▼ security
- Dependency health: 0.84 → unverified ▼ functional
- Package version: 0.16.3 → 0.16.6 functional
- Package version: 0.16.3 → 0.16.5 functional
- 15 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 13 Nov 26 −14
- Malware scan: pass → unverified ▼ security
- Known CVEs: fail → unverified ▼ security
- Stability: 0.00 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Schema quality: 4217 → 5394 ▼ functional
- Schema quality: 4217 → 5061 ▼ functional
- Schema quality: 4217 → 5052 ▼ functional
- Dependency health: 0.84 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Package version: 0.13.1 → 0.16.3 functional
- Package version: 0.13.1 → 0.16.2 functional
- Package version: 0.13.1 → 0.16.1 functional
- Package version: 0.13.1 → 0.15.0 functional
- Package version: 0.13.1 → 0.14.1 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed npm/cloudgpu-mcp@0.16.8
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | cloudgpu-app/cloudgpu-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/cloudgpu-app/cloudgpu-mcp/.github/workflows/publish.yml@refs/heads/main |
| Rekor log index | 4033342964 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:ab255f71469946c4cc2bc2a3f7c13335931340342dad9b136d5bda0eb70851a4a1627d26151feb9f3fcddf4e093b4bda5c9a31a11964a34aff8e98984 |
Background: How many MCP packages publish verified provenance →
Dependencies 99 packages
| Packages resolved | 99 |
|---|---|
| Stale | 34 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
apply_workspace Apply Workspace to running GPU ~106
Restore 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.
| Name | Type | Req | Description |
|---|---|---|---|
| instance_id | string | yes | – |
| user_confirmed | boolean | yes | – |
| version_id | string | yes | – |
No output schema declared.
No examples provided.
assess_task_fit Assess whether a task fits CloudGPU ~93
Read-only task suitability before quoting a GPU. Returns blockers, unverified requirements and evidence status; does not benchmark, approve spending or guarantee availability.
| Name | Type | Req | Description |
|---|---|---|---|
| expected_output_bytes | integer | – | – |
| needs_persistent_outputs | boolean | – | – |
| requires_kernel_control | boolean | – | – |
| requires_nested_virtualization | boolean | – | – |
| requires_resale | boolean | – | – |
| task_type | string | yes | – |
No output schema declared.
No examples provided.
cancel_job Cancel a job ~42
Stops a job: if a GPU was started it is destroyed and billing stops. Output not yet uploaded by the command is lost.
| Name | Type | Req | Description |
|---|---|---|---|
| job_id | string | yes | – |
No output schema declared.
No examples provided.
cancel_server_job_batch Cancel a server batch ~54
Cancel queued children without starting a GPU; request safe shutdown of active children. Preserve outputs first. Previously started whole-hour charges remain payable.
| Name | Type | Req | Description |
|---|---|---|---|
| batch_id | string | yes | – |
| user_confirmed | boolean | yes | – |
No output schema declared.
No examples provided.
compare_compute_costs Compare GPU billing periods and estimated task costs ~98
Read-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.
| Name | Type | Req | Description |
|---|---|---|---|
| gpu_count | integer | – | – |
| gpu_models | array | yes | – |
| hours | number | yes | – |
| max_spend_usd | number | yes | – |
| template | string | – | – |
No output schema declared.
No examples provided.
confirm_storage_budget Confirm storage budget transfer ~64
Moves 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.
| Name | Type | Req | Description |
|---|---|---|---|
| quote_id | string | yes | – |
| user_confirmed | boolean | yes | – |
No output schema declared.
No examples provided.
connect_account Connect this assistant to a CloudGPU account ~146
Use 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.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_name | string | yes | How the user will recognise this assistant, e.g. 'Claude Code on Yang's laptop' |
| expires_in_days | integer | – | – |
| max_concurrent | integer | – | GPUs or jobs this key may run at once |
| spend_limit_usd | number | yes | Total this key may ever spend, in USD; ask the user |
No output schema declared.
No examples provided.
create_instance Rent a GPU ~252
Rents 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.
| Name | Type | Req | Description |
|---|---|---|---|
| idle_minutes | integer | – | Destroy after the GPU has been idle this long; 0 turns it off; otherwise at least 10 |
| max_hours | number | yes | Hard time limit in hours (at most 24) |
| max_spend_usd | number | yes | Budget for this instance in USD (at most 50) |
| quote_id | string | yes | – |
| setup_script | string | – | Optional bash script run once as root in the background after the instance is handed over; output in /root/cloudgpu-setup.log |
| user_confirmed | boolean | yes | true only if the user explicitly approved this quote in the conversation |
No output schema declared.
No examples provided.
delete_file Delete a persistent file ~48
Permanently deletes a persistent file or cancels an unfinished upload. Files pinned by a Workspace version cannot be deleted.
| Name | Type | Req | Description |
|---|---|---|---|
| file_id | string | yes | – |
| user_confirmed | boolean | yes | – |
No output schema declared.
No examples provided.
delete_workspace_version Delete Workspace version ~49
Deletes a saved version, releasing its file references. Refuses versions pinned by active Jobs. Ask the user first.
| Name | Type | Req | Description |
|---|---|---|---|
| user_confirmed | boolean | yes | – |
| version_id | string | yes | – |
No output schema declared.
No examples provided.
diagnose_job Inspect Job failure and cost state ~50
Read-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.
| Name | Type | Req | Description |
|---|---|---|---|
| job_id | string | yes | – |
No output schema declared.
No examples provided.
download Download from the instance ~71
Copies a file or directory from the instance to this computer. Do this for every result before stop_instance: destroying an instance erases its disk.
| Name | Type | Req | Description |
|---|---|---|---|
| instance_id | string | yes | – |
| local_path | string | yes | Local destination file or directory, e.g. ./outputs/ |
| remote_path | string | yes | – |
No output schema declared.
No examples provided.
download_artifact Download a persistent file ~41
Streams a persistent file to this computer. Never overwrites an existing local file.
| Name | Type | Req | Description |
|---|---|---|---|
| file_id | string | yes | – |
| local_path | string | yes | – |
No output schema declared.
No examples provided.
estimate_cost Quote a rental ~147
Live 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.
| Name | Type | Req | Description |
|---|---|---|---|
| continent | string | – | Hard continent constraint, from list_rental_regions |
| gpu_count | integer | – | – |
| gpu_model | string | yes | GPU model exactly as list_gpus returns it |
| hours | number | yes | Expected run time in hours |
| template | string | – | Template id from list_templates; omit for a plain GPU with Python and CUDA |
| workspace_restore_required | boolean | – | Reserve a rental for restoring a saved Workspace. Excludes suppliers with known impaired restore routes. |
No output schema declared.
No examples provided.
finish_connect Finish connecting ~65
After 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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_account CloudGPU account ~29
Balance in USD, how many instances this account may run at once, and how many are running now.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_agent_readiness Read-only Agent self-check ~44
No 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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_compute_catalog Public GPU catalog ~25
GPU catalog, templates and billing without an API key. Does not rent anything.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_job Job status ~62
Status 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.
| Name | Type | Req | Description |
|---|---|---|---|
| job_id | string | yes | – |
No output schema declared.
No examples provided.
get_job_batch Inspect a Job batch ~42
Read-only status and cost summary for explicit Job IDs. Does not retry, cancel, create or claim independent supplier release verification.
| Name | Type | Req | Description |
|---|---|---|---|
| job_ids | array | yes | – |
No output schema declared.
No examples provided.
get_job_batch_receipt Read a private local batch receipt ~77
Read 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.
| Name | Type | Req | Description |
|---|---|---|---|
| batch_key | string | yes | – |
No output schema declared.
No examples provided.
get_server_job_batch Read a durable server batch ~40
Read persisted child Job states and costs after either client or server restarts. Does not create or retry resources.
| Name | Type | Req | Description |
|---|---|---|---|
| batch_id | string | yes | – |
No output schema declared.
No examples provided.
get_status Instance status ~55
Status (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.
| Name | Type | Req | Description |
|---|---|---|---|
| instance_id | string | yes | – |
No output schema declared.
No examples provided.
get_storage Persistent storage quota ~25
Storage availability, used bytes, reserved uploads and account quota. No money is spent.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_workspace_application Workspace application status ~57
Check file restoration on an existing GPU. This does not create, stop or restart a GPU. An uncertain result must be checked, never automatically resubmitted.
| Name | Type | Req | Description |
|---|---|---|---|
| instance_id | string | yes | – |
| version_id | string | yes | – |
No output schema declared.
No examples provided.
get_workspace_version Read Workspace version ~28
Read the path-to-file manifest for an owned version.
| Name | Type | Req | Description |
|---|---|---|---|
| version_id | string | yes | – |
No output schema declared.
No examples provided.
list_files List persistent files ~25
Persistent artifacts, model/data files and Workspace files. Availability depends on storage being enabled.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_gpus List GPUs ~110
GPU 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.
| Name | Type | Req | Description |
|---|---|---|---|
| gpu_model | string | – | Filter by name, e.g. 4090, A100, H20 |
| min_vram_gb | number | – | Only GPUs with at least this much VRAM per card |
No output schema declared.
No examples provided.
list_instances List instances ~30
Instances on this account: running, starting, and those stopped in the last 7 days, with cost.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_jobs List jobs ~25
Recent jobs on this account with status and cost.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
No output schema declared.
No examples provided.
list_models List hosted models ~49
Models 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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_regional_offers Inspect regional compute observations ~191
Anonymous, 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.
| Name | Type | Req | Description |
|---|---|---|---|
| after_id | string | – | – |
| country_code | string | – | – |
| gpu_count | integer | – | – |
| gpu_model | string | – | – |
| include_unavailable | boolean | – | – |
| limit | integer | – | – |
| user_country | string | – | – |
No output schema declared.
No examples provided.
list_rental_regions List rentable GPUs by continent ~68
Read-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.
| Name | Type | Req | Description |
|---|---|---|---|
| continent | string | – | – |
No output schema declared.
No examples provided.
list_task_templates List reusable Job task drafts ~41
Public, 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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_templates List templates ~51
Ready-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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_workspace_instances Running GPUs for Workspace restore ~32
Lists your running GPUs that this key may access. Budgeted Agent keys only see instances created by the same key.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_workspace_versions List Workspace versions ~26
List saved immutable versions of an owned Workspace.
| Name | Type | Req | Description |
|---|---|---|---|
| workspace_id | string | yes | – |
No output schema declared.
No examples provided.
list_workspaces List Workspaces ~20
Saved project Workspaces; versions are immutable file manifests.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
prepare_job_batch Review a bounded Job batch ~77
Local, 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.
| Name | Type | Req | Description |
|---|---|---|---|
| batch_key | string | yes | – |
| jobs | array | yes | – |
| total_budget_usd | number | yes | – |
No output schema declared.
No examples provided.
prepare_job_rerun Prepare a successful job for rerun ~69
Read-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.
| Name | Type | Req | Description |
|---|---|---|---|
| job_id | string | yes | – |
No output schema declared.
No examples provided.
prepare_model_deployment Prepare models and a ComfyUI workflow ~129
Preparation 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.
| Name | Type | Req | Description |
|---|---|---|---|
| model_references | array | yes | – |
| workflow | object | – | – |
No output schema declared.
No examples provided.
prepare_task_pipeline Prepare sequential tasks for one GPU allocation ~96
Local 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.
| Name | Type | Req | Description |
|---|---|---|---|
| persist_summary | boolean | – | – |
| steps | array | yes | – |
| workspace_version_id | string | – | – |
No output schema declared.
No examples provided.
prepare_task_template Prepare a Job task draft ~200
Local 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.
| Name | Type | Req | Description |
|---|---|---|---|
| accept_storage_charges | boolean | – | – |
| comfy_port | integer | – | – |
| dataset_path | string | – | – |
| entrypoint | string | – | – |
| image_count | integer | – | – |
| input_path | string | – | – |
| learning_rate | number | – | – |
| model_reference | object | – | – |
| output_files | array | – | – |
| persist_results | boolean | – | – |
| rank | integer | – | – |
| sequence_length | integer | – | – |
| steps | integer | – | – |
| target_modules | array | – | – |
| template_id | string | yes | – |
| timeout_seconds | integer | – | – |
| workflow_path | string | – | – |
| workspace_version_id | string | – | – |
No output schema declared.
No examples provided.
quote_compute Server-side compute quote ~122
Compare minute and whole-hour Job estimates, minimum charges and starting balances. No GPU is started. Use job_billing_options to compare cost for your duration, then call quote_job_billing for the selected period. The legacy quote_id still supports minute-only Jobs.
| Name | Type | Req | Description |
|---|---|---|---|
| disk_gb | integer | – | – |
| estimated_duration_seconds | integer | yes | – |
| gpu_count | integer | – | – |
| gpu_model | string | – | – |
| max_budget_usd | number | yes | – |
| min_vram_gb | integer | – | – |
| template | string | – | – |
No output schema declared.
No examples provided.
quote_job_billing Quote the selected Job billing period ~107
Read-only. Use the exact Job configuration and selected billing period from quote_compute. Show the returned billing period, minimum charge and hourly total. Obtain explicit approval before sending billingQuoteId as billing_quote_id with billing_accepted=true to run_job.
| Name | Type | Req | Description |
|---|---|---|---|
| billing_increment_seconds | – | yes | – |
| disk_gb | integer | – | – |
| gpu_count | integer | – | – |
| gpu_model | string | yes | – |
| template | string | – | – |
| workspace_restore_required | boolean | – | – |
No output schema declared.
No examples provided.
quote_storage_budget Quote separate storage budget ~75
Quote 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.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| amount_usd | number | yes | – |
No output schema declared.
No examples provided.
request_top_up Request an owner payment link ~58
Creates 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.
| Name | Type | Req | Description |
|---|---|---|---|
| amount_usd | number | yes | – |
No output schema declared.
No examples provided.
resolve_model_reference Pin a public model reference ~91
Read-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.
| Name | Type | Req | Description |
|---|---|---|---|
| files | array | yes | – |
| name | string | yes | – |
| repo_id | string | yes | – |
| revision | string | – | – |
No output schema declared.
No examples provided.
resume_artifact_upload Resume interrupted file upload ~73
Resume 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.
| Name | Type | Req | Description |
|---|---|---|---|
| file_id | string | yes | – |
| local_path | string | yes | – |
| sha256 | string | yes | – |
No output schema declared.
No examples provided.
run_command Run a command on the instance ~122
Runs 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.
| Name | Type | Req | Description |
|---|---|---|---|
| background | boolean | – | – |
| command | string | yes | bash command or script |
| instance_id | string | yes | – |
| timeout_sec | integer | – | Foreground only |
| workdir | string | – | Directory to run in |
No output schema declared.
No examples provided.
How do I install the CloudGPU MCP server?
CloudGPU MCP runs locally as an npm package, launched with npx -y cloudgpu-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · cloudgpu-mcp
claude mcp add cloudgpu-app-cloudgpu-mcp -- npx -y cloudgpu-mcp
What is the CloudGPU MCP server?
CloudGPU MCP is listed in the public MCP registry as io.github.cloudgpu-app/cloudgpu-mcp. Agent GPU compute scheduling: compare billing, approve budgets, run tasks and persist results. This page covers its npm package (cloudgpu-mcp).
Is the CloudGPU MCP server safe to use?
CloudGPU MCP scores 69 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the CloudGPU MCP server expose?
CloudGPU MCP exposes 60 tools: request_top_up, wait_for_funds, get_agent_readiness, assess_task_fit, list_rental_regions, and 55 more. Their descriptions and schemas cost roughly 5,127 tokens of context every time the server is loaded.
Is the CloudGPU MCP server still maintained?
CloudGPU MCP is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the CloudGPU MCP server under?
CloudGPU MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the CloudGPU MCP server?
VerifyMCP ran 15 checks on CloudGPU MCP, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about CloudGPU MCP: Malware scan. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.