# SpareHive GPU Advisor

- Registry name: `io.github.RichardXu001/sparehive-advisor` · version 0.1.0
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.RichardXu001%2Fsparehive-advisor
- Server page: https://mcpstation.net/s/io.github.RichardXu001--sparehive-advisor.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://sparehive.com/mcp`

## Tools (as reported by the server, not verified)

- `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。
- `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。
- `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。
- `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。

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html