# Tandiu Data MCP server

Source: https://glimind.com/server/mcp-registry%2Fcn.tandiu%2Fdata
Registry id: `mcp-registry/cn.tandiu/data`
Status: live (checked 2026-10-26T22:30:31.322Z)

## Measurements (30 days)

- Uptime: 99.79%
- Checks: 3343
- Outages (90 days): 7

## Install

```json
{
  "mcpServers": {
    "tandiu-data-mcp-server": {
      "type": "http",
      "url": "https://www.tandiu.cn/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http tandiu-data-mcp-server https://www.tandiu.cn/mcp
```

## Tools (14)

- `about_tandiu_data`: What data TANDIU publishes, refresh cadence, price basis and how to cite. Call first.
- `cheapest_model_for_score`: Cheapest models whose benchmark score meets a threshold (absolute or percent of the best score).
- `estimate_enterprise_ai_cost`: Monthly AI cost for 10 / 100 / 1,000 / 10,000-person company samples across industries: API (per-role model choice, or the open model's official API) vs self-ho
- `estimate_role_token_budget`: Monthly token usage and cost for 32 common job roles at light / standard / heavy AI usage, with the best model (any country) and the best Chinese model that mee
- `estimate_self_hosting`: VRAM, GPUs needed, single-stream and batched throughput, hardware cost and the vendor's official API price/speed for self-hosting an open-weights model. Omit mo
- `get_llm_price_history`: Pro (API key required): daily official list-price history per model since July 2026, USD and RMB per 1M tokens, with source URLs. Filter by model, vendor, count
- `get_price_index`: Chain-linked LLM price index (CN, US or all models), 30-day change, median price and series.
- `list_ai_funding`: Funding rounds of AI companies (mainly US and China): company, business, round, amount, valuation, investors, source links. Newest first; filter by region, sect
- `list_cloud_agents`: Cloud agents (one persistent agent per person, team agents, hosting platforms) with specs and monthly prices.
- `list_gpu_prices`: Data-center, workstation and consumer GPUs (B300/B200/H200/H100/H20, Ascend 910B/910C, RTX PRO 6000/5500/5000, RTX 5090/5090D/4090D, L40S/L20): VRAM, bandwidth,
- `list_llm_prices`: Official API list prices (USD per 1M tokens) with Artificial Analysis, LiveBench 2.0 and Epoch AI scores for major US and Chinese LLMs. Filter and sort.
- `list_overseas_listings`: Where Chinese open models (DeepSeek, Qwen, GLM, Kimi, MiniMax, ...) are listed on platforms headquartered outside mainland China: hosting type, regions, input/o
- `list_price_changes`: Official list-price cuts/increases observed in daily snapshots, and models newly added to tracking.
- `recommend_coding_pc`: Relative speed and tier (best/recommended/minimum/not_advised) of Macs, laptops and desktops for running Codex / Claude Code.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.