# SpareHive GPU Advisor

> Read-only GPU advisor: model VRAM needs, fit checks and rental prices, with evidence grades.

- name: io.github.RichardXu001/sparehive-advisor
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 97/100
- quality: 80/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.RichardXu001%2Fsparehive-advisor
- tools: https://api.protogrid.dev/v1/servers/io.github.RichardXu001%2Fsparehive-advisor/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "sparehive-advisor": {
      "type": "http",
      "url": "https://sparehive.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% +updated-24d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 80/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 75 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: search_models (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); model_requirements (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); fit_check (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 376 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump
- pass `tools.hidden_text`: no hidden text in tool names, descriptions, schemas or annotations

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name
- pass `stability.new_links`: no tool change named a new site

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 5, about 376 tokens to load them all
- tool set hash: a55f1612c5aa849f04104bb397505051
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.RichardXu001/sparehive-advisor.svg)](https://protogrid.dev/servers/io.github.RichardXu001/sparehive-advisor)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://sparehive.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (5)

- `data_status`: 报告数据的新鲜度：每个数据文件的更新时间、距今天数、是否超过 60 天阈值。当用户质疑数据是否过时时调用。
- `fit_check`: 判断某模型（指定量化、指定上下文）能否跑在某张显卡上。返回 fits/tight/no/unknown、剩余显存、内存拆解、以及跑不动时的替代方案（降量化/减上下文/换更大卡），并附带该卡的租金。
- `gpu_prices`: 查询租用不同类型 GPU 的价格：我们的即时档/排队档报价、host 实得、电费成本、竞品中位价与国内零售价。只有 RTX 4090 有报价，其余显示为未定。
- `model_requirements`: 查询部署某个模型需要的硬件配置：指定量化下的权重大小、最小/推荐显存、证据等级与出处，以及各张显卡的 fits/tight/no 判定与租价。数据可能过期，响应里会给出 data_updated 与 stale。
- `search_models`: 按名字或类型查找模型 ID。查询模型显存需求前先用它确认 ID；模型名有别名（Qwen3.8 27B / qwen3.8-27b）。返回 id、类型、最小显存、参数规模。