Back to search
100
MCP live MCP 2025-06-18 streamable-http

xyz.mingxinstorage/mingxin-mcp-server

xyz.mingxinstorage/mingxin-mcp-server

Measured AI-inference-storage benchmarks with citations, article search, KV-cache ROI estimation.

Uptime
100.0%
1 direct probes · 30d
Response
954ms
last probe
Tools
3
callable
Resources
0
readable
Prompts
0
available
Primary URL
https://www.mingxinstorage.xyz/api/mcp

Tools · 3

search_mingxin_docs

Search Mingxin's published articles on AI inference storage (KV cache tiering, NVMe-oF all-flash arrays, LLM serving). Returns titles, URLs and excerpts. Supports Chinese and English.

query_benchmark

Query Mingxin's signed benchmark results for FX-series storage acceleration: throughput +29-40%, TTFT -26-32% (480B model on 8x AMD MI308X), model loading 6.2-9.3x vs NFS, and the full R1-R9 report li…

estimate_roi

Estimate the ROI of adding a Mingxin FX100 KV-cache storage tier to a GPU inference cluster. Model is a faithful port of the reproducible Python model (accel_value.py). Results are mid-scenario estima…

How to use

Add to your Claude Desktop / Cursor / Cline MCP config:

{
  "mcpServers": {
    "xyz.mingxinstorage/mingxin-mcp-server": {
      "url": "https://www.mingxinstorage.xyz/api/mcp",
      "transport": "streamable-http"
    }
  }
}