WalnutLink A-share Depth Desk

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

使うべきか

品質と安全性

A
説明の品質
100%
スキーマの完全性
100%
命名の品質
80%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~641トークン数(ツール定義)
~840 B一般的なレスポンスサイズ
注意への影響は中程度(128k コンテキストの 0.50%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

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

リモートエンドポイント

https://walnutlink.ai/mcpstreamable-http

できること

ツール一覧

ツール(3)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
⚪a_share_deep_research(question)

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.

入力スキーマ

{
  "type": "object",
  "properties": {
    "question": {
      "type": "string",
      "description": "The judgement question, in Chinese or English. Name the company; a ticker alone is usually a quote request."
    }
  },
  "required": [
    "question"
  ]
}
⚪a_share_chain_edge(a, b, relation)

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.

入力スキーマ

{
  "type": "object",
  "properties": {
    "a": {
      "type": "string",
      "description": "Company A: 6-digit A-share code or Chinese name."
    },
    "b": {
      "type": "string",
      "description": "Company B: 6-digit code or name. An unlisted company name also works (e.g. an acquisition target)."
    },
    "relation": {
      "type": "string",
      "description": "Optional filter when the pair has more than one link.",
      "enum": [
        "supplier",
        "customer",
        "competitor",
        "peer",
        "equity",
        "investor",
        "none",
        "unknown"
      ]
    }
  },
  "required": [
    "a",
    "b"
  ]
}
🟢a_share_answer_by_id(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.

入力スキーマ

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "The 12-character hex id returned by a_share_deep_research, e.g. dc037a7fc6c8."
    }
  },
  "required": [
    "id"
  ]
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 3 件