# ScoutWyze Compute (npm · @scoutwyze/compute-mcp)

Ranks current RunPod GPU offers by price and freshness. Supports x402/USDC-on-Base payments.

- Trust score: 78/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@scoutwyze/compute-mcp`: 78/100 (this document), [markdown](https://verifymcp.io/servers/scoutwyze-max-compute-mcp/scoutwyze-compute-mcp.md), [page](https://verifymcp.io/servers/scoutwyze-max-compute-mcp/scoutwyze-compute-mcp)

## Channel facts

- Registry: `npm`
- Package: `@scoutwyze/compute-mcp`
- Version: `0.1.1`
- 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 2026-11-05.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 30 of 93 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 41 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 73/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 372 tokens (~186/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 2 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the ScoutWyze Compute MCP server?

ScoutWyze Compute runs locally as an npm package, launched with npx -y @scoutwyze/compute-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 scoutwyze-max-compute-mcp -- npx -y @scoutwyze/compute-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "scoutwyze-max-compute-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@scoutwyze/compute-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "scoutwyze-max-compute-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@scoutwyze/compute-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add scoutwyze-max-compute-mcp -- npx -y @scoutwyze/compute-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "scoutwyze-max-compute-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@scoutwyze/compute-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add scoutwyze-max-compute-mcp --command npx --arg -y --arg @scoutwyze/compute-mcp
```

### Hermes

```yaml
mcp_servers:
  scoutwyze-max-compute-mcp:
    command: "npx"
    args: ["-y", "@scoutwyze/compute-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "scoutwyze-max-compute-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@scoutwyze/compute-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add scoutwyze-max-compute-mcp -t stdio -c npx -a -y @scoutwyze/compute-mcp
```

### Other

```json
{
  "mcpServers": {
    "scoutwyze-max-compute-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@scoutwyze/compute-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.

### 2026-11-05 (score 78, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-11-01 (score 78, 0)

- [security] Stability: 0.97 → pass

### 2026-10-31 (score 78, 0)

- [functional] Stability: pass → 0.97

### 2026-10-25 (score 78, 0)

- [security] Stability: 0.97 → pass

### 2026-10-24 (score 78, −5)

- [security regression] CVE-2023-54404 affects this package: high
- [security regression] Known CVEs: pass → fail

### 2026-10-23 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (2)

### `scoutwyze_sample` (~79 tokens)

ScoutWyze Compute — free sample

Free, anonymous preview of a real ranked GPU offer from ScoutWyze Compute — ranks current RunPod GPU offers by price and freshness. Fixed query (cheapest preference), rate-limited per IP, never billed. Use this to see the real response shape and the current live price (billing.price_usd) before calling scoutwyze_rank.

### `scoutwyze_rank` (~293 tokens)

ScoutWyze Compute — rank GPU offers

Ranks current RunPod GPU offers by price and freshness for a given workload. Billed per successful match — the real price is in the response's billing.price_usd field; never assume a fixed amount, it can change server-side. Auth: if a SCOUTWYZE_API_KEY env var is configured, calls with a prepaid Bearer key (billing.rail: "bearer" in the response — never charged on a no-match result). If unauthenticated, or the key is invalid, this tool returns a real HTTP 402 x402 payment challenge (nonce, payTo, maxAmountRequired, expiresAt) as its result content, not an error — this server holds no private key and cannot pay it. A wallet-capable calling agent must settle the challenge independently and retry with the resulting X-PAYMENT proof (billing.rail: "x402" on success — settles before scoring, no refund on a no-match result, see SOT.md §5).

Input parameters:

- `gpuClass` (string): Filter by GPU model substring, e.g. "H100" (case-insensitive)
- `maxPricePerHour` (number): Maximum vendor hourly price in USD
- `minVramGb` (number): Minimum GPU memory in GB
- `preference` (string): Ranking strategy — defaults to cheapest
- `region` (string): Filter by region prefix (case-insensitive)

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/scoutwyze-max-compute-mcp/scoutwyze-compute-mcp#diagnostics

## Score history

- 2026-11-05: 78
- 2026-11-04: 78
- 2026-11-03: 78
- 2026-11-02: 78
- 2026-11-01: 78
- 2026-10-31: 78
- 2026-10-30: 78
- 2026-10-29: 78
- 2026-10-28: 78
- 2026-10-27: 78
- 2026-10-26: 78
- 2026-10-25: 78
- 2026-10-24: 78
- 2026-10-23: 83
- 2026-10-22: 82
- 2026-10-21: 82
- 2026-10-20: 81
- 2026-10-19: 81
- 2026-10-18: 80
- 2026-10-17: 80
- 2026-10-16: 79
- 2026-10-15: 79
- 2026-10-14: 78
- 2026-10-13: 78
- 2026-10-12: 78
- 2026-10-11: 77
- 2026-10-05: 74
- 2026-10-04: 74
- 2026-10-03: 73
- 2026-10-02: 73

## Common questions

### What is the ScoutWyze Compute MCP server?

ScoutWyze Compute is an MCP server listed in the public MCP registry as io.github.scoutwyze-max/compute-mcp. Ranks current RunPod GPU offers by price and freshness. Supports x402/USDC-on-Base payments. This page covers its npm package (@scoutwyze/compute-mcp).

### Is the ScoutWyze Compute MCP server safe to use?

ScoutWyze Compute scores 78 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. 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 ScoutWyze Compute MCP server expose?

ScoutWyze Compute exposes 2 tools: scoutwyze_sample, scoutwyze_rank. Their descriptions and schemas cost roughly 372 tokens of context every time the server is loaded.

### Is the ScoutWyze Compute MCP server still maintained?

ScoutWyze Compute 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 ScoutWyze Compute MCP server under?

ScoutWyze Compute 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 ScoutWyze Compute MCP server?

VerifyMCP ran 15 checks on ScoutWyze Compute, 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 ScoutWyze Compute: Security disclosure. 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.

## Links

- npm package: https://www.npmjs.com/package/@scoutwyze/compute-mcp
- Socket report: https://socket.dev/npm/package/@scoutwyze/compute-mcp
- Repository: https://github.com/scoutwyze-max/scoutwyze-compute
- Website: https://scoutwyze-compute.fly.dev/
- Changelog RSS feed: https://verifymcp.io/servers/scoutwyze-max-compute-mcp/scoutwyze-compute-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/scoutwyze-max-compute-mcp/scoutwyze-compute-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/scoutwyze-max-compute-mcp/scoutwyze-compute-mcp.json
- HTML version of this page: https://verifymcp.io/servers/scoutwyze-max-compute-mcp/scoutwyze-compute-mcp