The xyz.mingxinstorage/mingxin-mcp-server is an official MCP (Model Context Protocol) server for Mingxin (Tianjin) Semiconductor Equipment Co., Ltd. It provides signed AI-inference-storage benchmark data, technical article search, and KV-cache tiering ROI estimation. Benchmark figures include signed test-report citations (R1–R9).

🛠️ Key Features

Signed AI-inference-storage benchmark data with citations R1–R9
Technical article search
KV-cache tiering ROI estimation
Tool: query_benchmark for signed FX-series results, including throughput and TTFT changes

🚀 Use Cases

Retrieve reproducible benchmark results from mingxin-kvcache-bench
Use FX-series throughput and TTFT metrics for inference storage evaluation
Estimate KV-cache tiering ROI based on provided estimation outputs

⚡ Developer Benefits

Reproducible, open-source benchmark basis: mingxin-kvcache-bench
Citation-backed figures to support validation and review

⚠️ Limitations

Provided excerpt specifies only query_benchmark (FX-series throughput +29–40%, TTFT −26–32%) and does not list other tools.

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):

json

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

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

json

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

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.

xyz.mingxinstorage/mingxin-mcp-server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Mingxin MCP Server

Tools

Install

Remote (streamable HTTP, no install)

Domain-level discovery

Honesty & provenance

License

Install

Related servers