# ComputeNexa (pypi · computenexa-mcp)

Find, launch and stop private GPUs on ComputeNexa, with a quote before anything is charged.

- Trust score: 80/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-06

## Components

- pypi · `computenexa-mcp`: 80/100 (this document), [markdown](https://verifymcp.io/servers/computenexa-gpuinfrastructure-computenexa-mcp/computenexa-mcp.md), [page](https://verifymcp.io/servers/computenexa-gpuinfrastructure-computenexa-mcp/computenexa-mcp)

## Channel facts

- Registry: `pypi`
- Package: `computenexa-mcp`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-06.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 32 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to computenexa-gpuInfrastructure/computenexa-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 5 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1357 tokens (~90/item across 15 items; 15 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 83% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the ComputeNexa MCP server?

ComputeNexa runs locally as a PyPI package, launched with uvx computenexa-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add computenexa-gpuinfrastructure-computenexa-mcp -- uvx computenexa-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "computenexa-gpuinfrastructure-computenexa-mcp": {
      "command": "uvx",
      "args": [
        "computenexa-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "computenexa-gpuinfrastructure-computenexa-mcp": {
      "command": "uvx",
      "args": [
        "computenexa-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add computenexa-gpuinfrastructure-computenexa-mcp -- uvx computenexa-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "computenexa-gpuinfrastructure-computenexa-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "computenexa-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add computenexa-gpuinfrastructure-computenexa-mcp --command uvx --arg computenexa-mcp
```

### Hermes

```yaml
mcp_servers:
  computenexa-gpuinfrastructure-computenexa-mcp:
    command: "uvx"
    args: ["computenexa-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "computenexa-gpuinfrastructure-computenexa-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "computenexa-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add computenexa-gpuinfrastructure-computenexa-mcp -t stdio -c uvx -a computenexa-mcp
```

### Other

```json
{
  "mcpServers": {
    "computenexa-gpuinfrastructure-computenexa-mcp": {
      "command": "uvx",
      "args": [
        "computenexa-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-02 (score 80, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-01 (score 65)

First indexed and scored.

## MCP tools (15)

### `whoami` (~41 tokens)

Who am I

Who this server's API key acts as: email, team and role, the team's balance and GPU limit, and whether
the key may launch and stop machines.

Output parameters:

- `api_key`: The key this server uses; null if the platform doesn't report it
- `balance_usd` (number): The team's prepaid balance
- `can_launch`: Whether this server's key may launch, extend and stop machines
- `email` (string)
- `gpu_limit` (integer): GPUs the team may run at the same time
- `role`: Your role in the team: owner, admin or member
- `team`
- `team_members`

### `list_gpus` (~95 tokens)

List GPUs

GPUs with live prices (US dollars per GPU per hour) and stock, cheapest first.

Input parameters:

- `app`: Only GPUs that run this app (see list_apps), e.g. chat
- `include_sold_out` (boolean): Also list GPUs not for sale right now
- `min_memory_gb`: At least this much GPU memory
- `region` (string): any = anywhere; us; ca = Canada

Output parameters:

- `gpus` (array)
- `region` (string)

### `list_apps` (~93 tokens)

List apps

The apps a GPU can start with (basic, datascience, chat, imagegen, modelapi, voice): what each is for, the
models it offers and which model we recommend per GPU memory. Give `app` for the software installed.

Input parameters:

- `app`: One app, to also see what's installed in it
- `package`: With app: find this package's version, e.g. torch

Output parameters:

- `apps` (array)
- `software` (array): What's installed (when one app was asked for)

### `list_machines` (~66 tokens)

List machines

Your machines, newest first: state, GPU, app, price, time left and cost so far.

Input parameters:

- `active_only` (boolean): Only starting or running machines
- `limit` (integer)
- `whole_team` (boolean): The whole team's machines (owners and admins)

Output parameters:

- `machines` (array)

### `get_machine` (~62 tokens)

Get a machine

One machine: its state, how to connect (SSH command, browser apps, API or endpoint address), time left,
keep-running status and costs. Never its keys.

Input parameters:

- `machine_id` (string, required): e.g. cnx-7f3a9c

Output parameters:

- `api_base_url`: Model API / Voice Agent machines: their API address
- `app` (string)
- `billing`
- `browser_apps` (array): Apps to open from the dashboard's Open button while running
- `charged_usd` (number)
- `cost_so_far_usd` (number): What it costs if it ended now
- `end_reason`
- `endpoint_name`
- `endpoint_url`: Your own server on the machine's port 8000
- `expires_at`
- `gpu` (string)
- `gpu_count` (integer)
- `id` (string): e.g. cnx-7f3a9c
- `keep_running_hours`: Renews this many hours at a time; null = off
- `label`
- `launched_by`
- `model`
- `next_renewal_at`
- `price_per_hour_usd` (number): For the whole machine (all its GPUs)
- `project`
- `refunded_usd` (number)
- `region`
- `renew_failed` (boolean)
- `ssh_command`: While running, if the machine has an SSH key
- `startup_progress`
- `state` (string): requested | provisioning | running | stopping | terminated | failed
- `time_left_minutes`

### `get_usage` (~38 tokens)

Get usage

Spending and GPU-hours over the last N days, by GPU, app, day and project.

Input parameters:

- `days` (integer): The last N days

Output parameters:

- `balance_usd` (number)
- `by_app` (array)
- `by_gpu` (array)
- `daily` (array)
- `days` (integer)
- `gpu_hours` (number)
- `projects` (array)
- `sessions` (integer)
- `spend_usd` (number)
- `topups_usd` (number)

### `list_receipts` (~45 tokens)

List receipts

Finished sessions and what each cost in the end (charged minus refunded).

Input parameters:

- `days` (integer): Sessions that ended in the last N days
- `limit` (integer)

Output parameters:

- `receipts` (array)
- `total_net_usd` (number)

### `list_projects` (~26 tokens)

List projects

Saved projects (files restored into ~/work on machines launched with them) and their size.

Output parameters:

- `projects` (array)

### `list_endpoints` (~41 tokens)

List endpoints

Endpoints: stable HTTPS addresses for your own server on a machine's port 8000, and the machine each
points at now. Never their keys.

Output parameters:

- `endpoints` (array)

### `launch_machine` (~264 tokens)

Launch a machine

Launch a GPU machine. Costs money: call first with confirm=false to get a quote (nothing happens), show it
to the person, and only after they agree call again with the same arguments, confirm=true and
expected_total_usd. The booked time is charged up front from the team's balance.

Input parameters:

- `app` (string, required): App from list_apps, e.g. datascience
- `confirm` (boolean): false = only quote (default); true = launch, after the person agreed to the quote
- `endpoint`: Endpoint name or id this machine serves
- `expected_total_usd`: With confirm=true: the quote's total_usd the person agreed to
- `gpu` (string, required): GPU slug from list_gpus, e.g. rtx-a6000
- `gpu_count` (integer)
- `hours` (number, required): How long to book; unused time is refunded
- `keep_running_hours`: Renew this many hours at a time until stopped
- `label`: A name for the machine
- `model`: For apps with models; left out = our recommendation for this GPU
- `project`: Project name or id to restore into ~/work and save back
- `region` (string): Where it must run

Output parameters:

- `machine`
- `quote`
- `status` (string): quote = nothing happened yet; done = it was carried out

### `extend_machine` (~98 tokens)

Extend a machine

Add time to a machine at the price it launched with. Costs money: quote first (confirm=false), then
confirm=true with expected_total_usd once the person agrees.

Input parameters:

- `confirm` (boolean): false = only quote; true = extend, after the person agreed
- `expected_total_usd`: With confirm=true: the quoted total_usd
- `hours` (number, required): Time to add
- `machine_id` (string, required)

Output parameters:

- `machine`
- `quote`
- `status` (string): quote = nothing happened yet; done = it was carried out

### `set_keep_running` (~148 tokens)

Keep a machine running

Keep running: the machine renews itself `hours` at a time from the team's balance, at its launch price,
until it's stopped. Turning it on spends money at every renewal: quote first, then confirm=true with
expected_renewal_usd. Turning it off (hours=null) needs no confirmation.

Input parameters:

- `confirm` (boolean): Turning on: false = only quote; true = turn on, after the person agreed
- `expected_renewal_usd`: With confirm=true: the quoted renewal_usd
- `hours` (required): Renew this many hours at a time; null = turn off (it stops when its paid time ends)
- `machine_id` (string, required)

Output parameters:

- `machine`
- `quote`
- `status` (string): quote = nothing happened yet; done = it was carried out

### `stop_machine` (~58 tokens)

Stop a machine

End a machine now: stopped if running, cancelled with a full refund if still starting. Files outside a
project are deleted; a project is saved first. Unused time is refunded. Can't be undone.

Input parameters:

- `machine_id` (string, required)

Output parameters:

- `machine`
- `refunded_usd` (number)

### `create_endpoint` (~82 tokens)

Create an endpoint

A new Endpoint (owners and admins): a stable HTTPS address and key for your own server on port 8000, e.g.
one per customer you serve. Launch machines for it with launch_machine(endpoint=...). Free. Its key is shown
once here; get_endpoint_key shows it again.

Input parameters:

- `name` (string, required): e.g. the customer it serves

Output parameters:

- `id` (string)
- `key`: Only when just created, or from get_endpoint_key
- `machine`: The machine it points at now, if any
- `name` (string)
- `url` (string)

### `get_endpoint_key` (~45 tokens)

Get an endpoint's key

An Endpoint's key (owners and admins). Only when the person asks for it: it gives access to their
server.

Input parameters:

- `endpoint` (string, required): Endpoint name or id

Output parameters:

- `endpoint` (string)
- `key` (string)
- `url` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/computenexa-gpuinfrastructure-computenexa-mcp/computenexa-mcp#diagnostics

## Score history

- 2026-11-06: 80
- 2026-11-05: 80
- 2026-11-04: 80
- 2026-11-03: 80
- 2026-11-02: 80
- 2026-11-01: 65

## Common questions

### What is the ComputeNexa MCP server?

ComputeNexa is an MCP server listed in the public MCP registry as io.github.computenexa-gpuInfrastructure/computenexa-mcp. Find, launch and stop private GPUs on ComputeNexa, with a quote before anything is charged. This page covers its PyPI package (computenexa-mcp).

### Is the ComputeNexa MCP server safe to use?

ComputeNexa scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 6 November 2026. 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 ComputeNexa MCP server expose?

ComputeNexa exposes 15 tools: whoami, list_gpus, list_apps, list_machines, get_machine, and 10 more. Their descriptions and schemas cost roughly 1,202 tokens of context every time the server is loaded.

### Is the ComputeNexa MCP server still maintained?

ComputeNexa is still listed as active in the MCP registry. We last reached this channel on 6 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 ComputeNexa MCP server under?

ComputeNexa 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 ComputeNexa MCP server?

VerifyMCP ran 15 checks on ComputeNexa, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about ComputeNexa: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/computenexa-mcp/
- Socket report: https://socket.dev/pypi/package/computenexa-mcp
- Repository: https://github.com/computenexa-gpuInfrastructure/computenexa-mcp
- Website: https://computenexa.com/
- Changelog RSS feed: https://verifymcp.io/servers/computenexa-gpuinfrastructure-computenexa-mcp/computenexa-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/computenexa-gpuinfrastructure-computenexa-mcp/computenexa-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/computenexa-gpuinfrastructure-computenexa-mcp/computenexa-mcp.json
- HTML version of this page: https://verifymcp.io/servers/computenexa-gpuinfrastructure-computenexa-mcp/computenexa-mcp