CloudGPU MCP
NPM · CLOUDGPU-MCP
Rent a per-minute GPU from your MCP client, run a job, download results, shut it down.
Available components
Last scanned (17 minutes ago)
Scores higher than 61% 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 Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 34 of 100 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to mrhy7176/cloudgpu-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 1 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability80
- 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 1303 tokens (~93/item across 14 items; 13 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 Coverage83
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 48% 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 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 15 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
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.
- 4 Nov 26 +6
- Known CVEs: unverified → fail ▼ security
- Dependency health: unverified → 0.84 ▲ functional
- 3 Nov 26 +11
- Known CVEs: fail → unverified ▼ security
- Malware scan: unverified → pass ▲ security
- Dependency health: 0.84 → unverified ▼ functional
- Package version: 0.1.2 → 0.3.0 functional
- Package version: 0.1.2 → 0.2.0 functional
- 2 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- Package version: 0.1.1 → 0.1.2 functional
- 1 Nov 26 +1
- Security disclosure: unverified → fail ▼ functional
- 31 Oct 26 +1
- Security disclosure: fail → unverified ▼ functional
- Stability: unverified → 0.13 ▲ functional
- Package version: 0.1.0 → 0.1.1 functional
- 28 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 27 Oct 26 60
First indexed and scored.
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 5 Nov 2026 · Analysed npm/cloudgpu-mcp@0.3.0
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 | mrhy7176/cloudgpu-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/mrhy7176/cloudgpu-mcp/.github/workflows/publish.yml@refs/heads/main |
| Rekor log index | 3665424874 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:f8d2615a80a674edc0ec800b3647bf4280645c44ae6cbee9ef2fd73ed7c17d5086dfe9f8c6ac556d322e4e284430f9f869f2c5ca52584df9ccfe1fb40 |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 100 packages
| Packages resolved | 100 |
|---|---|
| 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 →
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.
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.
estimate_cost Quote a rental ~105
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 |
|---|---|---|---|
| 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 |
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_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.
list_gpus List GPUs ~90
GPU models you can rent now, with VRAM, live price per GPU-hour in USD and availability (ok / low / none). Prices are live; never assume them.
| 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_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_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.
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.
stop_instance Destroy an instance ~68
Destroys 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).
| Name | Type | Req | Description |
|---|---|---|---|
| force | boolean | – | – |
| instance_id | string | yes | – |
No output schema declared.
No examples provided.
tail_logs Job logs and GPU use ~75
Last 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.
| Name | Type | Req | Description |
|---|---|---|---|
| instance_id | string | yes | – |
| job_id | string | – | – |
| lines | integer | – | – |
| path | string | – | – |
No output schema declared.
No examples provided.
upload Upload to the instance ~108
Copies 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.
| Name | Type | Req | Description |
|---|---|---|---|
| allow_sensitive | boolean | – | – |
| instance_id | string | yes | – |
| local_path | string | yes | – |
| remote_path | string | yes | Destination on the instance, e.g. /root/project or /root/data/ |
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 mrhy7176-cloudgpu-mcp -- npx -y cloudgpu-mcp
What is the CloudGPU MCP server?
CloudGPU MCP is listed in the public MCP registry as io.github.mrhy7176/cloudgpu-mcp. Rent a per-minute GPU from your MCP client, run a job, download results, shut it down. This page covers its npm package (cloudgpu-mcp).
Is the CloudGPU MCP server safe to use?
CloudGPU MCP scores 79 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 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 13 tools: get_account, list_gpus, list_templates, estimate_cost, list_models, and 8 more. Their descriptions and schemas cost roughly 1,105 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 5 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.