# TANDIU AI infrastructure data (remote · www.tandiu.cn)

Free, no auth. Daily CN AI infra: LLM prices, index, trends, GPU, estimators, agents, PC, funding.

- Trust score: 80/100 (high trust)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `www.tandiu.cn`: 80/100 (this document), [markdown](https://verifymcp.io/servers/cn-tandiu-data/www.md), [page](https://verifymcp.io/servers/cn-tandiu-data/www)

## Channel facts

- Endpoint: `https://www.tandiu.cn/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.4`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 1797 tokens (~112/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 87/100
  - Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 77/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 31% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the TANDIU AI infrastructure data MCP server?

TANDIU AI infrastructure data is a hosted endpoint at https://www.tandiu.cn/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http cn-tandiu-data 'https://www.tandiu.cn/mcp'
```

### Cursor

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

### VS Code

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

### Codex

```toml
[mcp_servers.cn-tandiu-data]
url = "https://www.tandiu.cn/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cn-tandiu-data": {
      "type": "remote",
      "url": "https://www.tandiu.cn/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add cn-tandiu-data --url 'https://www.tandiu.cn/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  cn-tandiu-data:
    url: "https://www.tandiu.cn/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "cn-tandiu-data": {
      "Transport": "http",
      "Url": "https://www.tandiu.cn/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add cn-tandiu-data -t streamable-http -u 'https://www.tandiu.cn/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 78, +3)

- [security improvement] HSTS header: fail → pass

### 2026-10-31 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 74, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 1560 → 1797
- [functional] New tool “find_mcp”
- [functional] New tool “get_mcp_changes”

### 2026-10-29 (score 74, +1)

- [security] Tool “list_gpu_prices” rewrote its description, which is the text the model reads

### 2026-10-27 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-24 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (16)

### `about_tandiu_data` (~31 tokens)

Overview of TANDIU datasets

What data TANDIU publishes, refresh cadence, price basis and how to cite. Call first.

### `list_llm_prices` (~96 tokens)

LLM API prices and benchmarks

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.

Input parameters:

- `country` (string): US, CN or another ISO code
- `limit` (integer)
- `query` (string): substring of model name
- `sort_by` (string)
- `vendor` (string)

### `cheapest_model_for_score` (~66 tokens)

Cheapest model at a benchmark score

Cheapest models whose benchmark score meets a threshold (absolute or percent of the best score).

Input parameters:

- `country` (string)
- `limit` (integer)
- `metric` (string)
- `min_percent_of_top` (number)
- `min_score` (number)

### `get_price_index` (~50 tokens)

LLM price index

Chain-linked LLM price index (CN, US or all models), 30-day change, median price and series.

Input parameters:

- `group` (string)
- `since` (string): YYYY-MM-DD

### `get_llm_price_history` (~120 tokens)

LLM official price history (Pro)

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, country and date range.

Input parameters:

- `country` (string)
- `limit` (integer)
- `model` (string): model key or name substring, e.g. gpt-5.6, deepseek
- `since` (string): YYYY-MM-DD
- `until` (string): YYYY-MM-DD
- `vendor` (string)

### `list_price_changes` (~59 tokens)

Recorded LLM price changes

Official list-price cuts/increases observed in daily snapshots, and models newly added to tracking.

Input parameters:

- `limit` (integer)
- `min_change_pct` (number)
- `since` (string): YYYY-MM-DD, default last 90 days

### `estimate_self_hosting` (~106 tokens)

Self-hosting sizing

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 model to list available models.

Input parameters:

- `gpus` (array): gpu ids from list_gpu_prices, e.g. h100_sxm, h20, ascend910b, rtx_pro_6000, rtx5090, rtx5090d
- `model` (string)

### `list_gpu_prices` (~172 tokens)

GPU prices and specs

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, FP16 compute, list price, China market price (SXM GPUs per 8-GPU node), cloud rental with 7-day change and daily median history (since 2026-10-18; few_samples flags thin markets), sources and dates.

Input parameters:

- `china_available_only` (boolean)
- `query` (string): gpu id or name substring, e.g. h20, rtx pro 6000, 910
- `with_cloud_rental` (boolean)

### `estimate_role_token_budget` (~92 tokens)

Token budget per job role

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 meet each role's capability floor.

Input parameters:

- `group` (string)
- `limit` (integer)
- `query` (string): role id or name, e.g. backend, lawyer, doctor
- `usage` (string)

### `estimate_enterprise_ai_cost` (~165 tokens)

Enterprise AI infrastructure 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-hosting the same open model on public cloud, private cloud or on-premises GPUs, with GPU count and cost per 1M tokens.

Input parameters:

- `headcount` (integer)
- `include_gpu_breakdown` (boolean): self-hosting cost on every GPU for each sample
- `include_hardware_table` (boolean): per-GPU unit economics (throughput, hardware price, cost per 1M tokens)
- `include_team` (boolean)
- `query` (string): industry or sample, e.g. bank, hospital, ecommerce

### `list_cloud_agents` (~51 tokens)

Cloud agents compared

Cloud agents (one persistent agent per person, team agents, hosting platforms) with specs and monthly prices.

Input parameters:

- `kind` (string)
- `limit` (integer)
- `query` (string)

### `recommend_coding_pc` (~59 tokens)

Computers for AI coding agents

Relative speed and tier (best/recommended/minimum/not_advised) of Macs, laptops and desktops for running Codex / Claude Code.

Input parameters:

- `category` (string)
- `query` (string)
- `tier` (string)

### `list_ai_funding` (~120 tokens)

AI funding rounds

Funding rounds of AI companies (mainly US and China): company, business, round, amount, valuation, investors, source links. Newest first; filter by region, sector, company/investor name, date or minimum amount.

Input parameters:

- `limit` (integer)
- `min_amount_usd` (number)
- `query` (string): company, product or investor name
- `region` (string)
- `sector` (string)
- `since` (string): YYYY-MM-DD
- `sort_by` (string)

### `list_overseas_listings` (~165 tokens)

Chinese LLMs on overseas platforms

Where Chinese open models (DeepSeek, Qwen, GLM, Kimi, MiniMax, ...) are listed on platforms headquartered outside mainland China: hosting type, regions, input/output/blended USD per 1M tokens vs the official price, context, tool calling, data-policy links. Labs ranked by Hugging Face followers, models by downloads and likes.

Input parameters:

- `limit` (integer)
- `max_blended_usd` (number): max blended USD per 1M tokens
- `model` (string): model name or key substring, e.g. deepseek v4 pro, kimi, glm-5
- `platform` (string): platform name substring, e.g. together, bedrock
- `tool_calling` (boolean)

### `find_mcp` (~143 tokens)

Big Tech MCP Access Tracker

Official MCP servers of major US / Chinese / regional companies (payments, maps, finance data, collaboration, cloud, model platforms): transport, auth barrier, account requirements, pricing model, free quota (doc wording), daily cross-border reachability measured by TANDIU (China<->US handshake; evidence=probe), listing on MCP Registry / Claude directory. Facts only, no scores.

Input parameters:

- `category` (string)
- `cross_border` (string)
- `limit` (integer)
- `pricing_model` (string)
- `query` (string): vendor or product substring, e.g. stripe, 高德
- `region` (string)

### `get_mcp_changes` (~68 tokens)

Big Tech MCP access change events

Append-only change events of tracked official MCP servers (terms/pricing pages, cross-border reachability, tools, status, directory listing) for the last N days, optionally for one entry id from find_mcp.

Input parameters:

- `days` (integer)
- `entry_id` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/cn-tandiu-data/www#diagnostics

## Score history

- 2026-11-05: 80
- 2026-11-04: 79
- 2026-11-03: 79
- 2026-11-02: 78
- 2026-11-01: 78
- 2026-10-31: 75
- 2026-10-30: 74
- 2026-10-29: 74
- 2026-10-28: 73
- 2026-10-27: 73
- 2026-10-26: 72
- 2026-10-25: 72
- 2026-10-24: 72
- 2026-10-23: 71
- 2026-10-22: 71
- 2026-10-21: 70
- 2026-10-20: 70
- 2026-10-19: 69
- 2026-10-18: 69
- 2026-10-17: 68
- 2026-10-16: 68
- 2026-10-15: 67
- 2026-10-14: 66
- 2026-10-13: 66
- 2026-10-12: 66
- 2026-10-10: 65

## Common questions

### What is the TANDIU AI infrastructure data MCP server?

TANDIU AI infrastructure data is an MCP server listed in the public MCP registry as cn.tandiu/data. Free, no auth. Daily CN AI infra: LLM prices, index, trends, GPU, estimators, agents, PC, funding. This page covers its hosted endpoint (https://www.tandiu.cn/mcp).

### Is the TANDIU AI infrastructure data MCP server safe to use?

TANDIU AI infrastructure data scores 80 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the TANDIU AI infrastructure data MCP server expose?

TANDIU AI infrastructure data exposes 16 tools: about_tandiu_data, list_llm_prices, cheapest_model_for_score, get_price_index, get_llm_price_history, and 11 more. Their descriptions and schemas cost roughly 1,563 tokens of context every time the server is loaded.

### Does the TANDIU AI infrastructure data MCP server require authentication?

No. We connected to TANDIU AI infrastructure data without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the TANDIU AI infrastructure data MCP server still maintained?

TANDIU AI infrastructure data is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the TANDIU AI infrastructure data MCP server?

VerifyMCP ran 13 checks on TANDIU AI infrastructure data, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://www.tandiu.cn/mcp
- Website: https://www.tandiu.cn/en
- Changelog RSS feed: https://verifymcp.io/servers/cn-tandiu-data/www.xml
- Changelog JSON feed: https://verifymcp.io/servers/cn-tandiu-data/www/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/cn-tandiu-data/www.json
- HTML version of this page: https://verifymcp.io/servers/cn-tandiu-data/www