← sparehive.com

INDIVIDUAL MCP TOOL

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。

sparehive.comnone authenticationAvailability not checked

LIVE ENDPOINT

https://sparehive.com/mcp

No auth detected

Connect to this endpoint to inspect the live schema for gpu_prices and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Inferred read-only · medium confidence · heuristic, not a guarantee.

  • No write-capable action terms were found; this is not proof that invocation has no side effects.

Parent server

sparehive.com

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.sparehive-advisor]
url = "https://sparehive.com/mcp"
enabled = true
Claude Code

.mcp.json

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

Settings → Connectors → Add custom connector

Name: sparehive-advisor
Remote MCP URL: https://sparehive.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "sparehive-advisor": {
      "url": "https://sparehive.com/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "sparehive-advisor": {
      "type": "http",
      "url": "https://sparehive.com/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "sparehive-advisor",
  "transport": "streamable-http",
  "url": "https://sparehive.com/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

Related tools

  • 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.
  • 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。
  • 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。