# corpusAI Cloud Pricing (npm · corpus-cloud-pricing-mcp)

Cloud spot, on-demand, reserved and GPU rental prices with index fixings, paid per call over x402.

- Trust score: 63/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-27

## Components

- remote · `cloud.trycorpus.ai`: 70/100, [markdown](https://verifymcp.io/servers/jtraversa-corpus-cloud-pricing-mcp/cloud.md), [page](https://verifymcp.io/servers/jtraversa-corpus-cloud-pricing-mcp/cloud)
- npm · `corpus-cloud-pricing-mcp`: 63/100 (this document), [markdown](https://verifymcp.io/servers/jtraversa-corpus-cloud-pricing-mcp/corpus-cloud-pricing-mcp.md), [page](https://verifymcp.io/servers/jtraversa-corpus-cloud-pricing-mcp/corpus-cloud-pricing-mcp)

## Channel facts

- Registry: `npm`
- Package: `corpus-cloud-pricing-mcp`
- Version: `0.1.5`
- 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 2026-09-27.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 32 of 114 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1923 tokens (~68/item across 28 items; 28 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**: 87/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 60% 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 28 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 29 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.

**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 corpusAI Cloud Pricing MCP server?

corpusAI Cloud Pricing runs locally as an npm package, launched with npx -y corpus-cloud-pricing-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 jtraversa-corpus-cloud-pricing-mcp -- npx -y corpus-cloud-pricing-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "jtraversa-corpus-cloud-pricing-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "corpus-cloud-pricing-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "jtraversa-corpus-cloud-pricing-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "corpus-cloud-pricing-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add jtraversa-corpus-cloud-pricing-mcp -- npx -y corpus-cloud-pricing-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jtraversa-corpus-cloud-pricing-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "corpus-cloud-pricing-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add jtraversa-corpus-cloud-pricing-mcp --command npx --arg -y --arg corpus-cloud-pricing-mcp
```

### Hermes

```yaml
mcp_servers:
  jtraversa-corpus-cloud-pricing-mcp:
    command: "npx"
    args: ["-y", "corpus-cloud-pricing-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "jtraversa-corpus-cloud-pricing-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "corpus-cloud-pricing-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add jtraversa-corpus-cloud-pricing-mcp -t stdio -c npx -a -y corpus-cloud-pricing-mcp
```

### Other

```json
{
  "mcpServers": {
    "jtraversa-corpus-cloud-pricing-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "corpus-cloud-pricing-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.

### 2026-09-26 (score 63)

First indexed and scored.

## MCP tools (28)

### `catalog` (~29 tokens)

Free. Providers, region slugs, coverage windows, prices per call and the source legend. Call first.

### `instances` (~73 tokens)

Free. Instance types available in a region with coverage dates.

Input parameters:

- `prefix` (string): Type-name prefix filter, e.g. c5.
- `provider` (string, required): Cloud provider
- `region` (string, required): Region slug from the catalog tool (e.g. us-east-1, us-central1, us-east)

### `gpu_models` (~21 tokens)

Free. Normalised GPU model names with quote counts and providers.

### `index_tickers` (~31 tokens)

Free. Every index ticker (CX.<MODEL>.<SEGMENT>) with segment definitions and the methodology version.

### `status` (~16 tokens)

Free. Freshness of every data source.

### `spot_daily` (~121 tokens)

Paid (0.05 USDC). Full daily spot price history of one instance type, all eras, source per row.

Input parameters:

- `from` (string): Start, ISO 8601 UTC
- `instance` (string, required): Instance type exactly as listed by the instances tool (e.g. c5.large)
- `provider` (string, required): Cloud provider
- `region` (string, required): Region slug from the catalog tool (e.g. us-east-1, us-central1, us-east)
- `to` (string): End, ISO 8601 UTC

### `spot_hourly` (~119 tokens)

Paid (0.01 USDC). Hourly time-weighted OHLC spot bars for one instance type.

Input parameters:

- `from` (string): Start, ISO 8601 UTC
- `instance` (string, required): Instance type exactly as listed by the instances tool (e.g. c5.large)
- `provider` (string, required): Cloud provider
- `region` (string, required): Region slug from the catalog tool (e.g. us-east-1, us-central1, us-east)
- `to` (string): End, ISO 8601 UTC

### `spot_events` (~125 tokens)

Paid (0.01 USDC). Raw spot price-change events for one instance type with zone and timestamp.

Input parameters:

- `from` (string): Start, ISO 8601 UTC
- `instance` (string, required): Instance type exactly as listed by the instances tool (e.g. c5.large)
- `limit` (integer)
- `provider` (string, required): Cloud provider
- `region` (string, required): Region slug from the catalog tool (e.g. us-east-1, us-central1, us-east)
- `to` (string): End, ISO 8601 UTC

### `spot_latest` (~86 tokens)

Paid (0.01 USDC). Current spot price per zone for one instance type.

Input parameters:

- `instance` (string, required): Instance type exactly as listed by the instances tool (e.g. c5.large)
- `provider` (string, required): Cloud provider
- `region` (string, required): Region slug from the catalog tool (e.g. us-east-1, us-central1, us-east)

### `spot_snapshot` (~65 tokens)

Paid (0.10 USDC). Current spot price of every type and zone in a region.

Input parameters:

- `provider` (string, required): Cloud provider
- `region` (string, required): Region slug from the catalog tool (e.g. us-east-1, us-central1, us-east)

### `spot_monthly` (~90 tokens)

Paid (0.05 USDC). Monthly spot history back to 2014 for legacy AWS types.

Input parameters:

- `instance` (string, required): Instance type exactly as listed by the instances tool (e.g. c5.large)
- `provider` (string, required): Cloud provider
- `region` (string, required): Region slug from the catalog tool (e.g. us-east-1, us-central1, us-east)

### `ondemand` (~87 tokens)

Paid (0.01 USDC). On-demand list-price change history of one instance type.

Input parameters:

- `instance` (string, required): Instance type exactly as listed by the instances tool (e.g. c5.large)
- `provider` (string, required): Cloud provider
- `region` (string, required): Region slug from the catalog tool (e.g. us-east-1, us-central1, us-east)

### `reserved` (~92 tokens)

Paid (0.01 USDC). AWS reserved-instance effective hourly price history (1y/3y, no/all upfront).

Input parameters:

- `instance` (string, required): Instance type exactly as listed by the instances tool (e.g. c5.large)
- `region` (string, required): Region slug from the catalog tool (e.g. us-east-1, us-central1, us-east)
- `ri_type` (string)

### `gpu_quotes` (~69 tokens)

Paid (0.01 USDC). Latest GPU rental quotes for one model across neo-clouds and marketplaces, USD per GPU-hour.

Input parameters:

- `gpu` (string, required): Model from gpu_models, e.g. "H100 SXM"
- `market` (string)
- `provider` (string)

### `gpu_index` (~65 tokens)

Paid (0.05 USDC). Daily lo/median/mean/hi per provider and market for one GPU model, with aws-spot and gcp-spot legs.

Input parameters:

- `from` (string)
- `gpu` (string, required)
- `to` (string)

### `index_fixing` (~63 tokens)

Paid (0.01 USDC). One day's index fixing for a ticker such as CX.H100SXM.NEO (median USD per GPU-hour, lo, hi, n).

Input parameters:

- `day` (string): YYYY-MM-DD
- `ticker` (string, required)

### `index_history` (~55 tokens)

Paid (0.05 USDC). Daily fixings for a ticker; SPOT tickers reach back to 2022.

Input parameters:

- `from` (string)
- `ticker` (string, required)
- `to` (string)

### `index_board` (~31 tokens)

Paid (0.10 USDC). Every ticker's fixing for one day.

Input parameters:

- `day` (string)

### `capacity_stress` (~69 tokens)

Paid (0.01 USDC). Capacity stress score for one GPU model on one day, 0 slack … 100 tight, with every component (availability, io.net units, Vast supply, spot-to-on-demand ratio).

Input parameters:

- `day` (string)
- `gpu` (string, required)

### `capacity_history` (~46 tokens)

Paid (0.05 USDC). Daily capacity stress scores for one GPU model.

Input parameters:

- `from` (string)
- `gpu` (string, required)
- `to` (string)

### `capacity_board` (~38 tokens)

Paid (0.10 USDC). Every GPU model's capacity stress score for one day, tightest first.

Input parameters:

- `day` (string)

### `tokens_models` (~38 tokens)

Free. Every LLM with a token price fixing: canonical slug, ticker codes, sources, hosts and today's price range, plus the frontier basket.

### `tokens_quotes` (~67 tokens)

Paid (0.01 USDC). Every source and host's price for one model on one day, USD per million input/output tokens.

Input parameters:

- `day` (string)
- `model` (string, required): Canonical slug from tokens_models, e.g. "claude-sonnet-5"

### `tokens_fixing` (~62 tokens)

Paid (0.01 USDC). One day's token price fixing for CX.TOK.<MODEL>.IN, .OUT or .BLEND, or CX.TOK.FRONTIER.<side>.

Input parameters:

- `day` (string)
- `ticker` (string, required)

### `tokens_history` (~45 tokens)

Paid (0.05 USDC). Daily fixings for a token ticker.

Input parameters:

- `from` (string)
- `ticker` (string, required)
- `to` (string)

### `tokens_board` (~40 tokens)

Paid (0.10 USDC). Every model's input, output and blended fixing for one day plus the frontier basket.

Input parameters:

- `day` (string)

### `term_instance` (~102 tokens)

Paid (0.01 USDC). Price ladder for one instance type: spot, on-demand, 1-year and 3-year commitments with discount to on-demand.

Input parameters:

- `instance` (string, required): Instance type exactly as listed by the instances tool (e.g. c5.large)
- `provider` (string, required): Cloud provider
- `region` (string, required): Region slug from the catalog tool (e.g. us-east-1, us-central1, us-east)

### `term_curve` (~72 tokens)

Paid (0.05 USDC). Term structure per hyperscaler for one GPU model, USD per GPU-hour: spot, on-demand, 1y, 3y with discounts.

Input parameters:

- `gpu` (string, required): Model with a hyperscaler mapping, e.g. "H100 SXM", "T4"

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/jtraversa-corpus-cloud-pricing-mcp/corpus-cloud-pricing-mcp#diagnostics

## Score history

- 2026-09-27: 63
- 2026-09-26: 63

## Common questions

### What is the corpusAI Cloud Pricing MCP server?

corpusAI Cloud Pricing is an MCP server listed in the public MCP registry as io.github.JTraversa/corpus-cloud-pricing-mcp. Cloud spot, on-demand, reserved and GPU rental prices with index fixings, paid per call over x402. This page covers its npm package (corpus-cloud-pricing-mcp).

### Is the corpusAI Cloud Pricing MCP server safe to use?

corpusAI Cloud Pricing scores 63 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 27 September 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 corpusAI Cloud Pricing MCP server expose?

corpusAI Cloud Pricing exposes 28 tools: catalog, instances, gpu_models, index_tickers, status, and 23 more. Their descriptions and schemas cost roughly 1,817 tokens of context every time the server is loaded.

### Is the corpusAI Cloud Pricing MCP server still maintained?

corpusAI Cloud Pricing is still listed as active in the MCP registry. We last reached this channel on 27 September 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 corpusAI Cloud Pricing MCP server under?

corpusAI Cloud Pricing declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/corpus-cloud-pricing-mcp
- Socket report: https://socket.dev/npm/package/corpus-cloud-pricing-mcp
- Website: https://cloud.trycorpus.ai/docs
- Changelog RSS feed: https://verifymcp.io/servers/jtraversa-corpus-cloud-pricing-mcp/corpus-cloud-pricing-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/jtraversa-corpus-cloud-pricing-mcp/corpus-cloud-pricing-mcp.json
- HTML version of this page: https://verifymcp.io/servers/jtraversa-corpus-cloud-pricing-mcp/corpus-cloud-pricing-mcp