# GPU Finder (remote · gpufinder.dev)

GPU prices, observed stock and seven-day availability history. Read-only; free API key.

- Trust score: 92/100 (high trust)
- Change this week: +7
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `gpufinder.dev`: 92/100 (this document), [markdown](https://verifymcp.io/servers/dev-gpufinder-gpufinder/gpufinder.md), [page](https://verifymcp.io/servers/dev-gpufinder-gpufinder/gpufinder)
- npm · `gpufinder`: 49/100, [markdown](https://verifymcp.io/servers/dev-gpufinder-gpufinder/gpufinder-2.md), [page](https://verifymcp.io/servers/dev-gpufinder-gpufinder/gpufinder-2)

## Channel facts

- Endpoint: `https://gpufinder.dev/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.1.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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.

- **Endpoint Security**: 94/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 84/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1029 tokens (~114/item across 9 items; 8 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 80/100
  - Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 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).

## Install

### How do I install the GPU Finder MCP server?

GPU Finder is a hosted endpoint at https://gpufinder.dev/mcp, so there is nothing to install locally. 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 --transport http dev-gpufinder-gpufinder 'https://gpufinder.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-gpufinder-gpufinder": {
      "url": "https://gpufinder.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-gpufinder-gpufinder": {
      "type": "http",
      "url": "https://gpufinder.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-gpufinder-gpufinder]
url = "https://gpufinder.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-gpufinder-gpufinder": {
      "type": "remote",
      "url": "https://gpufinder.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-gpufinder-gpufinder --url 'https://gpufinder.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-gpufinder-gpufinder:
    url: "https://gpufinder.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-gpufinder-gpufinder": {
      "Transport": "http",
      "Url": "https://gpufinder.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-gpufinder-gpufinder -t streamable-http -u 'https://gpufinder.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-gpufinder-gpufinder": {
      "type": "http",
      "url": "https://gpufinder.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-11-04 (score 92, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 91, +3)

- [functional] The server now declares the “resources” capability
- [functional] The server now declares the “prompts” capability
- [functional] First check of Schema quality: 100
- [functional] Schema quality: excellent → good
- [functional] New prompt “find_gpu_rental”
- [functional] New resource “pricing-and-stock”

### 2026-11-01 (score 88, 0)

- [security] Tool “get_market_snapshot” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 112 → 125
- [cosmetic] “get_market_snapshot” added an optional parameter “provider”
- [cosmetic] “get_market_snapshot” added an optional parameter “region”

### 2026-10-30 (score 88, +3)

- [security improvement] Authorization: fail → pass
- [security] First check of Authorization: partial
- [security] Tool “get_prices” rewrote its description, which is the text the model reads
- [security] Tool “get_usage” rewrote its description, which is the text the model reads
- [security] Tool “list_gpus” rewrote its description, which is the text the model reads
- [security] Tool “list_providers” rewrote its description, which is the text the model reads
- [security] Tool “get_availability” rewrote its description, which is the text the model reads
- [security] Tool “get_data_status” rewrote its description, which is the text the model reads
- [security] Tool “get_market_snapshot” rewrote its description, which is the text the model reads
- [security] Tool “get_price_history” rewrote its description, which is the text the model reads
- [functional improvement] Schema quality: 126 → 112
- [cosmetic] Tool “get_prices” changed its title: Compare GPU prices
- [cosmetic] Tool “list_gpus” changed its title: List GPU models
- [cosmetic] Tool “list_providers” changed its title: List GPU providers
- [cosmetic] Tool “get_usage” changed its title: Check account usage
- [cosmetic] Tool “get_availability” changed its title: Check GPU availability
- [cosmetic] Tool “get_data_status” changed its title: Check data freshness
- [cosmetic] Tool “get_market_snapshot” changed its title: Find the cheapest available GPU
- [cosmetic] Tool “get_price_history” changed its title: View GPU price history

### 2026-10-28 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

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

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 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 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (8)

### `list_gpus` (~86 tokens)

List GPU models

List the GPU models GPU Finder tracks: canonical name and slug, VRAM, memory type, bandwidth, interconnect, provider and instance counts, and min/max hourly USD price. Returns canonical GPU identifiers and hardware specifications. Pages default to 20 rows, maximum 100; each page costs one data unit.

Input parameters:

- `page` (object): Pagination. Omit for the first page.

### `list_providers` (~93 tokens)

List GPU providers

List GPU cloud providers: name and slug, GPU and instance counts, min/max hourly USD price, egress cost per GB and free egress allowance, website and GPU Finder links, and last update time. Returns canonical provider identifiers and provider-level summaries. Pages default to 20 rows, maximum 100; each page costs one data unit.

Input parameters:

- `page` (object): Pagination. Omit for the first page.

### `get_prices` (~144 tokens)

Compare GPU prices

List every provider offer for one GPU model and node size: provider, instance type, region, GPU count, on-demand and spot USD price per whole node hour, links and last update. Prices reflect collected data, not a live capacity guarantee. Pages default to 20 rows, maximum 100; each page costs one data unit.

Input parameters:

- `count` (integer): GPUs per node. Prices are for the whole node. Defaults to 1.
- `gpu` (string, required): GPU model name, case-insensitive, e.g. "H100", "RTX 4090". See list_gpus.
- `page` (object): Pagination. Omit for the first page.

### `get_availability` (~164 tokens)

Check GPU availability

Show day-by-day stock for one GPU model over the last seven days, per provider and node size: available configuration-hours versus known configuration-hours each day, summed across tracked instances. Optionally limit to one provider. Reports observed availability history, not provider uptime or launch guarantees. Days without observations are unknown, not zero. Pages default to 20 rows, maximum 100; each page costs one data unit.

Input parameters:

- `gpu` (string, required): GPU model name, case-insensitive, e.g. "H100", "RTX 4090". See list_gpus.
- `page` (object): Pagination. Omit for the first page.
- `provider` (string): Provider name or slug, e.g. "runpod", "lambda". See list_providers.

### `get_price_history` (~162 tokens)

View GPU price history

Show how one GPU model's price changed month by month per provider: on-demand and spot USD per whole node hour for up to 12 UTC months. Pages default to 20 rows, maximum 100; each page costs one data unit. Reuse the same filters and page limit with nextCursor.

Input parameters:

- `count` (integer): GPUs per node. Prices are for the whole node. Defaults to 1.
- `gpu` (string, required): GPU model name, case-insensitive, e.g. "H100", "RTX 4090". See list_gpus.
- `months` (integer): UTC months of history per provider, 1-12. Defaults to 12.
- `page` (object): Pagination. Omit for the first page.

### `get_data_status` (~64 tokens)

Check data freshness

Report how fresh GPU Finder's data is: when price and availability collection last completed, and each provider's last success, last run, consecutive failures and last error. Includes timestamps for assessing data staleness. Costs one data unit; it is not an anonymous health check.

### `get_market_snapshot` (~240 tokens)

Find the cheapest available GPU

Check a GPU configuration once or in a client-scheduled availability watch: cheapest listed and freshly observed in-stock offers for one GPU model and exact GPU count, with whole-node/per-GPU hourly USD price, observation time, provider and region. Optional provider and exact provider-reported region filters run before regional aggregation and are echoed in filters. Compare snapshots in client-owned state; ignore timestamp-only changes. The server does not schedule checks or send notifications. One data unit per call; get_usage is free. Stock is not a launch guarantee.

Input parameters:

- `count` (integer): GPUs per node. Prices are for the whole node. Defaults to 1.
- `gpu` (string, required): GPU model name, case-insensitive, e.g. "H100", "RTX 4090". See list_gpus.
- `provider` (string): Provider name or slug, e.g. "runpod", "lambda". See list_providers.
- `region` (string): Exact provider-reported region, case-insensitive (e.g. Japan or eu-north1). Obtain labels from get_prices. Not a broad Europe/Asia filter or a placement guarantee.

### `get_usage` (~51 tokens)

Check account usage

Show this account's usage across REST and MCP: plan allowance, units used and remaining, and UTC reset times. Spends no monthly units and works after the monthly allowance is exhausted, but is still rate limited.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-gpufinder-gpufinder/gpufinder#diagnostics

## Score history

- 2026-11-05: 92
- 2026-11-04: 92
- 2026-11-03: 91
- 2026-11-02: 91
- 2026-11-01: 88
- 2026-10-31: 88
- 2026-10-30: 88
- 2026-10-29: 85
- 2026-10-28: 85
- 2026-10-27: 84
- 2026-10-26: 84
- 2026-10-25: 83
- 2026-10-24: 83
- 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: 74
- 2026-10-15: 74
- 2026-10-14: 73
- 2026-10-13: 73
- 2026-10-12: 72

## Common questions

### What is the GPU Finder MCP server?

GPU Finder is an MCP server listed in the public MCP registry as dev.gpufinder/gpufinder. GPU prices, observed stock and seven-day availability history. Read-only; free API key. This page covers its hosted endpoint (https://gpufinder.dev/mcp).

### Is the GPU Finder MCP server safe to use?

GPU Finder scores 92 out of 100 on VerifyMCP. 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 GPU Finder MCP server expose?

GPU Finder exposes 8 tools: list_gpus, list_providers, get_prices, get_availability, get_price_history, and 3 more. Their descriptions and schemas cost roughly 1,004 tokens of context every time the server is loaded.

### Does the GPU Finder MCP server require authentication?

Yes. GPU Finder asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the GPU Finder MCP server still maintained?

GPU Finder 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.

## Links

- Remote endpoint: https://gpufinder.dev/mcp
- Authorisation metadata: https://gpufinder.dev/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/gpufinder/mcp
- Website: https://gpufinder.dev/api
- Changelog RSS feed: https://verifymcp.io/servers/dev-gpufinder-gpufinder/gpufinder.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-gpufinder-gpufinder/gpufinder.json
- HTML version of this page: https://verifymcp.io/servers/dev-gpufinder-gpufinder/gpufinder