TANDIU AI infrastructure data

by tandiu.cn · remote · no sign-in to list tools · v0.1.4 · published by cn.tandiu

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

Changes · 6

Compare Registry entry

14 tools: 6 change things and 8 only read.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone0Claude Code: ask
Changes things6Claude Code: ask: see these tools
Only reads8Claude Code: allow: see these tools

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

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

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

14 tools

Changes things 6Creates or changes something that can be changed back.Claude Code: ask

about_tandiu_dataWhat data TANDIU publishes, refresh cadence, price basis and how to cite.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
What data TANDIU publishes, refresh cadence, price basis and how to cite. Call first.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cheapest_model_for_scoreCheapest models whose benchmark score meets a threshold (absolute or percent of the best score).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Cheapest models whose benchmark score meets a threshold (absolute or percent of the best score).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
estimate_enterprise_ai_costMonthly 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 …No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
estimate_role_token_budgetMonthly 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 capabi…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
estimate_self_hostingVRAM, GPUs needed, single-stream and batched throughput, hardware cost and the vendor's official API price/speed for self-hosting an open-weights model.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
recommend_coding_pcRelative speed and tier (best/recommended/minimum/not_advised) of Macs, laptops and desktops for running Codex / Claude Code.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Relative speed and tier (best/recommended/minimum/not_advised) of Macs, laptops and desktops for running Codex / Claude Code.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

Only reads 8Looks things up and changes nothing.Claude Code: allow

get_llm_price_historyPro (API key required): daily official list-price history per model since July 2026, USD and RMB per 1M tokens, with source URLs.No findings
Why it is in this group
- The name "get_llm_price_history" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_price_indexChain-linked LLM price index (CN, US or all models), 30-day change, median price and series.No findings
Why it is in this group
- The name "get_price_index" says "get": a word for reading.
Description, as the server wrote it
Chain-linked LLM price index (CN, US or all models), 30-day change, median price and series.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_ai_fundingFunding rounds of AI companies (mainly US and China): company, business, round, amount, valuation, investors, source links.No findings
Why it is in this group
- The name "list_ai_funding" says "list": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_cloud_agentsCloud agents (one persistent agent per person, team agents, hosting platforms) with specs and monthly prices.No findings
Why it is in this group
- The name "list_cloud_agents" says "list": a word for reading.
Description, as the server wrote it
Cloud agents (one persistent agent per person, team agents, hosting platforms) with specs and monthly prices.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_gpu_pricesData-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 …No findings
Why it is in this group
- The name "list_gpu_prices" says "list": a word for reading.
Description, as the server wrote it
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, sources and dates.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_llm_pricesOfficial API list prices (USD per 1M tokens) with Artificial Analysis, LiveBench 2.0 and Epoch AI scores for major US and Chinese LLMs.No findings
Why it is in this group
- The name "list_llm_prices" says "list": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_overseas_listingsWhere Chinese open models (DeepSeek, Qwen, GLM, Kimi, MiniMax, ...) are listed on platforms headquartered outside mainland China: hosting type, regions, input/output/blended USD pe…No findings
Why it is in this group
- The name "list_overseas_listings" says "list": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_price_changesOfficial list-price cuts/increases observed in daily snapshots, and models newly added to tracking.No findings
Why it is in this group
- The name "list_price_changes" says "list": a word for reading.
Description, as the server wrote it
Official list-price cuts/increases observed in daily snapshots, and models newly added to tracking.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.1.4. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__data__list_llm_prices",
      "mcp__data__get_price_index",
      "mcp__data__get_llm_price_history",
      "mcp__data__list_price_changes",
      "mcp__data__list_gpu_prices",
      "mcp__data__list_cloud_agents",
      "mcp__data__list_ai_funding",
      "mcp__data__list_overseas_listings"
    ],
    "ask": [
      "mcp__data__about_tandiu_data",
      "mcp__data__cheapest_model_for_score",
      "mcp__data__estimate_self_hosting",
      "mcp__data__estimate_role_token_budget",
      "mcp__data__estimate_enterprise_ai_cost",
      "mcp__data__recommend_coding_pc"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as data. Review it before you use it.

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/cn.tandiu/data/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

6 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry. Synced Oct 21, 2026, 17:46 UTC.

For agents: Markdown · JSON · report this listing