WalnutLink A-share Depth Desk

ai.walnutlink由 walnutlink.ai 發布官方發布者v1.3.0更新於 Oct 26, 2026

China A-share filings: why a number moved, does the trend continue, who supplies whom.

已驗證Streamable HTTP可網頁執行金融知識與記憶

概覽

AI 產生的概覽

遠端研究台，解釋中國 A 股公司財務數字變動的原因，答案可追溯至申報文件與投資人關係紀錄。

可以做什麼
  • 追問毛利率、現金流或存貨等項目為何變動，或某項政策對某上市公司損益表哪一行的影響
  • 查詢兩家中國公司之間的供應、競爭與股權關係，每條關係都附有申報文件中的原文引述
  • 依先前回傳的 id 取回研究結果，查看排隊狀態或取得含來源行的完整答案
適用情境
適合詢問中國上市公司已申報數字背後的原因、經營階層的公開說法、政策影響，或產業鏈上兩家公司的關係。不適用於即時報價、估值快照、目標價或買賣建議。
執行需求
需要可連線的遠端 Streamable HTTP 端點，提問不需驗證。答案由人工與代理程式協作產出，新問題可能只回傳排隊位置與 id，需稍後再取。身分僅影響排隊順序與每日額度。
安裝前請注意
第一個問題免費，之後每個問題需要一張票券，可透過在網站公開發表內容或每日造訪取得。問題內容會傳送給第三方服務。答案可能需要數分鐘到數小時，部分問題會明確回覆無法回答而非估算。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 WalnutLink A-share Depth Desk，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/ai.walnutlink%2Fwalnutlink-a-share/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "walnutlink-a-share-depth-desk": {
      "type": "http",
      "url": "https://walnutlink.ai/mcp"
    }
  }
}

README

WalnutLink A-share Depth Desk

An MCP server that answers why something moved in a Chinese listed company — and refuses to answer anything a quote app already tells you.

Endpoint: https://walnutlink.ai/mcp (Streamable HTTP, no auth for read)

What it is for

A language model already knows the price. What it does not know is why the gross margin dropped 1.6 points last quarter, which line of the filing moved, and whether the number came from the consolidated statement or the parent-company one.

This desk reads the filed report, the IR transcript and the disclosure wording, then answers in numbers with the page or announcement number attached.

Use it for:

  • a margin, cash flow or inventory line that moved and the reason behind it
  • what management actually said on the record, quoted from the transcript
  • a policy that landed and which line of which company's P&L it hits
  • two companies in the same chain diverging, and which line explains the gap
  • an industry-chain shift (HBM, 1.6T optics, domestic equipment) traced to filings

Do not use it for:

  • current price, change percent, PE, PB, market cap, turnover — the server returns 410 gone_by_design for these, on purpose
  • buy/sell recommendations, target prices, stop losses — it will not produce them
  • index-level point predictions

That refusal is the product. Depth is the only thing here worth paying attention to.

Tools

a_share_deep_research

json
{  "name": "a_share_deep_research",  "arguments": { "question": "为什么海康威视2026Q3单季毛利率环比下降了？" }}

Returns one of three things:

CaseWhat comes back
This question was researched beforethe vetted answer, immediately, with sources
It was not, but the primary evidence is already heldthe evidence plus an id for the human answer
Neithera queue position (你排第 3 位，大约 15 分钟) and an id

Answers are written by a human-plus-agent loop that reads primary sources, then pass four gates before publication: length, presence of a source line, no buy/sell language, at least one number. Answers that fail get reworked. Questions that cannot be answered from a primary source after four hours come back with an explicit "I could not answer this" rather than a guess.

a_share_answer_by_id

json
{ "name": "a_share_answer_by_id", "arguments": { "id": "dc037a7fc6c8" } }

Fetch that answer. While the question is still queued it returns the queue position (排第 2 位，大约 10 分钟) and explicitly says it is not an answer yet; once it is done it returns the full text with the source line. No credentials, no polling subscription, no HTML page to open.

This exists because of a review, not a plan: Glama scored the single-tool version A / 4.3 and marked Completeness down to 3/5 with one sentence — "it returns an id for a human answer with no tool to fetch that answer." That was correct. An automated client that cannot render HTML was handed a dead end.

Connect

Claude / Cursor / Cline / any MCP client with remote HTTP support

json
{  "mcpServers": {    "walnutlink-a-share": {      "url": "https://walnutlink.ai/mcp"    }  }}

Streamable HTTP, protocol versions 2025-06-18, 2025-03-26, 2024-11-05.

Also available over plain REST for platforms that cannot speak MCP: POST https://walnutlink.ai/api/ask — see https://walnutlink.ai/openapi.json.

Contracts

  • No auth is required to ask. Identity (WalnutLink Passport, Ed25519, self-issued) only affects queue position and daily quota.
  • First question is free. After that, one ticket per question; a ticket comes from leaving something public on the site, or from showing up daily.
  • Every answer carries a source line: company name, document, date, announcement number.
  • If a number cannot be traced to a filing, it is not published.

Machine-readable rules: https://walnutlink.ai/skill.md · https://walnutlink.ai/llms.txt

Registry

Published on the official MCP Registry as ai.walnutlink/walnutlink-a-share (versions 1.0.0, 1.1.0). DNS-verified against walnutlink.ai:

walnutlink.ai. TXT "v=MCPv1; k=ed25519; p=6XlUMDN+DQZgtWbv2NJiQrEFx0YilaqplkIYAsA3+5g="

Static server card: https://walnutlink.ai/.well-known/mcp/server-card.json

License

MIT. See LICENSE.

The answers themselves are research output, not software, and carry no warranty. Nothing here is investment advice.

來源：README.md，提交 8bbd51a

工具

3

a_share_deep_research

Use when the user asks WHY something happened or WHAT it means for a Chinese listed company: a margin moved, a policy landed, an industry chain shifted, two companies diverge, or what management actually said on the record. This desk does NOT serve quotes, price checks or valuation snapshots - that is commodity data available everywhere, and answering it would waste your turn. What it does: reads the filed report, the IR transcript and the disclosure wording, then answers in numbers. Returns a vetted answer immediately if this question has been researched before; otherwise it returns the primary-source evidence it already holds plus an id for the human answer. Ask it the question you would ask a sell-side analyst, not the one you would type into a quote app.

輸入參數question必填

a_share_chain_edge

Use when the user asks HOW two Chinese companies relate: who supplies whom, who competes with whom, who owns equity in whom, or whether an acquisition target overlaps with the acquirer's product line. Every relationship returned carries a verbatim quote from a filed document (annual report, prospectus, restructuring draft, related-party announcement) and a confidence tag: primary = the filing says it outright, secondary = broker or media, inferred = our deduction with no direct textual proof. Unlisted companies work as inputs too, which matters for acquisition targets. If the pair has not been researched it says so plainly instead of guessing - absence of a record is not evidence of no relationship. Do NOT call this for prices, valuation or index levels.

輸入參數a必填b必填relation

a_share_answer_by_id

Retrieve a research result by the id that a_share_deep_research returned. Call this to check whether the human-reviewed answer is ready, or to fetch the full text once it is. Answers take minutes to hours because a filed report is read first; while it is still queued the tool returns the queue position, not a guess. Use this instead of opening the public page when you are an automated client that cannot render HTML.

輸入參數id必填

版本歷史

2
  1. v1.3.0最新Oct 26, 2026
  2. v1.2.0Oct 25, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分