¿Qué puedes hacer con mingxin mcp server?

Mingxin MCP Server

Official MCP server for Mingxin (Tianjin) Semiconductor Equipment Co., Ltd. — signed AI-inference-storage benchmark data, technical article search, and KV-cache tiering ROI estimation.

Every figure this server returns carries a signed test-report citation (R1–R9). The underlying benchmark is open source and reproducible: mingxin-kvcache-bench.

Tools

Tool	What it does
`query_benchmark`	Signed FX-series results: throughput +29–40%, TTFT −26–32% (Qwen3-480B class on 8× AMD MI308X), model loading 6.2–9.3× vs NFS; full R1–R9 report list with hosted PDF URLs
`search_mingxin_docs`	Search Mingxin's published articles on KV cache tiering, NVMe-oF all-flash storage and LLM serving (Chinese + English)
`estimate_roi`	KV-cache tiering ROI estimate for a GPU cluster (faithful port of the reproducible Python model; mid-scenario estimates, not commitments)

Install

Remote (streamable HTTP, no install)

Endpoint: https://mingxinstorage.xyz/api/mcp

Cursor (~/.cursor/mcp.json):

{
  "mcpServers": {
    "mingxin": { "url": "https://mingxinstorage.xyz/api/mcp" }
  }
}

Claude Desktop / VS Code and other stdio-only clients (via this npm package):

{
  "mcpServers": {
    "mingxin": { "command": "npx", "args": ["-y", "mingxin-mcp-server"] }
  }
}

Domain-level discovery

https://mingxinstorage.xyz/.well-known/mcp.json

Honesty & provenance

Measured numbers come only from signed/official test reports; vendor specs and estimates are labeled as such.
ROI outputs are mid-scenario estimates with stated bands (uplift 29–40% measured; cold-recovery share 10–50% estimated, to be backfilled by pilot measurement).
This server exposes only already-public website content; no customer data.

License

MIT

Instalación

Añade mingxin mcp server a tu cliente. Elige el que uses.

{
  "servers": {
    "mingxin-mcp-server": {
      "type": "http",
      "url": "https://www.mingxinstorage.xyz/api/mcp"
    }
  }
}

Add to `.vscode/mcp.json` in your workspace.

claude mcp add mingxin-mcp-server -- npx -y mingxin-mcp-server

codex mcp add mingxin-mcp-server -- npx -y mingxin-mcp-server

amp mcp add mingxin-mcp-server -- npx -y mingxin-mcp-server

{
  "mcpServers": {
    "mingxin-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "mingxin-mcp-server"
      ]
    }
  }
}

Add to `claude_desktop_config.json`, then restart Claude Desktop.

{
  "mcpServers": {
    "mingxin-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "mingxin-mcp-server"
      ]
    }
  }
}

Add to `~/.cursor/mcp.json`, or `.cursor/mcp.json` for a single project.

{
  "mcpServers": {
    "mingxin-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "mingxin-mcp-server"
      ]
    }
  }
}

Add to `~/.codeium/windsurf/mcp_config.json`.

{
  "mcpServers": {
    "mingxin-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "mingxin-mcp-server"
      ]
    }
  }
}

Add to `cline_mcp_settings.json` via the MCP Servers panel.

{
  "mcpServers": {
    "mingxin-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "mingxin-mcp-server"
      ]
    }
  }
}

Add to `~/.gemini/settings.json`.

{
  "mcpServers": {
    "mingxin-mcp-server": {
      "type": "local",
      "command": "npx",
      "args": [
        "-y",
        "mingxin-mcp-server"
      ],
      "tools": [
        "*"
      ]
    }
  }
}

Add to `~/.copilot/mcp-config.json`, or run `/mcp add` inside the CLI.

{
  "context_servers": {
    "mingxin-mcp-server": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "mingxin-mcp-server"
        ]
      }
    }
  }
}

Add to your Zed `settings.json`.

npx -y mingxin-mcp-server

Run `goose configure`, choose **Add Extension → Command-line Extension**, and paste this command.

3 herramientas

mingxin mcp server expone 3 herramientas a un agente conectado.

query_benchmark: Signed FX-series results: throughput +29–40%, TTFT −26–32% (Qwen3-480B class on 8× AMD MI308X), model loading 6.2–9.3× vs NFS; full R1–R9 report list with hosted PDF URLs
search_mingxin_docs: Search Mingxin's published articles on KV cache tiering, NVMe-oF all-flash storage and LLM serving (Chinese + English)
estimate_roi: KV-cache tiering ROI estimate for a GPU cluster (faithful port of the reproducible Python model; mid-scenario estimates, not commitments)

Puntuación

69 / 100

Buena

Documentación18/25
Mantenimiento16/25
Confianza16/20
Capacidad4/15
Instalación15/15

Documents what it does and how to connect
Has a resolvable package or endpoint
Exposes at least one tool, prompt or resource
README has substantive content
Includes a code example
Documents its configuration
Mentions credentials or security posture
Last commit 38 days ago
Has a release history
Repository is not archived
Licensed MIT
Namespace verified in the official MCP registry
Claimed by its owner
Published under an organisation
3 tool(s) documented
Provides prompt templates
Provides resources
18 documented install method(s)
Published to a package registry
Offers a hosted endpoint — no local install

Leer los criterios completos →

Historial de versiones

Versiones	Publicada
1.0.0Última	25 jul 2026