# `io.github.RichardXu001/sparehive-advisor` on anlyon.dev

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://anlyon.dev/servers/io.github.RichardXu001/sparehive-advisor
- JSON: https://anlyon.dev/api/v1/servers/io.github.RichardXu001/sparehive-advisor
- Version: 0.1.0 (active)
- Publisher: io.github.RichardXu001 (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/RichardXu001/sparehive
- Metadata from the official MCP Registry, synced 2026-10-21T18:18:53.481Z

Title and description, as the publisher wrote them:

```untrusted-server-text
SpareHive GPU Advisor
Read-only GPU advisor: model VRAM needs, fit checks and rental prices, with evidence grades.
```

Scanned 2026-10-21T19:04:42.420Z over streamable-http.

**5 tools: 3 change things and 2 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 3 | ask |
| Only reads | read | 2 | allow |

## Findings

No check matched anything in these tool definitions.


## Changes things (3)

Creates or changes something that can be changed back. Claude Code: ask.

### `fit_check`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
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`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
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`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
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。
```

## Only reads (2)

Looks things up and changes nothing. Claude Code: allow.

### `data_status`

- The name "data_status" says "status": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
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。
```

### `search_models`

- The name "search_models" says "search": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
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。
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `sparehive-advisor`:

```json
{
  "permissions": {
    "allow": [
      "mcp__sparehive-advisor__search_models",
      "mcp__sparehive-advisor__data_status"
    ],
    "ask": [
      "mcp__sparehive-advisor__model_requirements",
      "mcp__sparehive-advisor__fit_check",
      "mcp__sparehive-advisor__gpu_prices"
    ],
    "deny": []
  }
}
```