About mingxin-mcp-server
mingxin-mcp-server exposes signed AI inference storage benchmarks, article search, and KV-cache tiering ROI estimates for teams evaluating infrastructure. Results distinguish measured data from estimates and link benchmark figures to reports.
Key features
- 01Signed benchmark results with report citations
- 02Search Chinese and English technical articles
- 03Estimate KV-cache tiering ROI
- 04Separate measurements from estimates
Use cases
- 01Compare AI inference storage benchmarks
- 02Research KV-cache tiering and LLM serving
- 03Estimate GPU-cluster tiering ROI
MCP support
It exposes benchmark queries, document search, and ROI estimation as MCP tools. Clients can connect through the hosted streamable HTTP endpoint or the npm package over stdio.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://www.mingxinstorage.xyz/api/mcpclaude mcp add --transport http xyz-mingxinstorage-mingxin https://www.mingxinstorage.xyz/api/mcp{"mcpServers":{"xyz-mingxinstorage-mingxin":{"type":"http","url":"https://www.mingxinstorage.xyz/api/mcp"}}}Open in Cursor{"servers":{"xyz-mingxinstorage-mingxin":{"type":"http","url":"https://www.mingxinstorage.xyz/api/mcp"}}}Open in VS Code{"mcpServers":{"xyz-mingxinstorage-mingxin":{"type":"http","url":"https://www.mingxinstorage.xyz/api/mcp"}}}{"mcpServers":{"xyz-mingxinstorage-mingxin":{"serverUrl":"https://www.mingxinstorage.xyz/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEMingxin 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
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.