Search / ai.walnutlink/walnutlink-a-share
protogridR0· no sign-inChina A-share filings: why a number moved, does the trend continue, who supplies whom.
v1.3.0 · active · repository · website · descriptor JSON · versions
{
"mcpServers": {
"walnutlink-a-share": {
"type": "http",
"url": "https://walnutlink.ai/mcp"
}
}
}claude mcp add --transport http walnutlink-a-share https://walnutlink.ai/mcp[mcp_servers.walnutlink-a-share]
url = "https://walnutlink.ai/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"walnutlink-a-share": {
"type": "remote",
"url": "https://walnutlink.ai/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"walnutlink-a-share": {
"type": "http",
"url": "https://walnutlink.ai/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=walnutlink-a-share&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vd2FsbnV0bGluay5haS9tY3AifQ%3D%3D"
}{
"servers": {
"walnutlink-a-share": {
"type": "http",
"url": "https://walnutlink.ai/mcp"
}
}
}{
"mcpServers": {
"walnutlink-a-share": {
"httpUrl": "https://walnutlink.ai/mcp"
}
}
}extensions:
"walnutlink-a-share":
enabled: true
name: "walnutlink-a-share"
type: streamable_http
uri: "https://walnutlink.ai/mcp"
timeout: 300
protocol.modernprotocol.statelessprotocol.transportprotocol.list_ttlauth.prm, auth.as_metadata, auth.cimdauth.secret_in_urltools.descriptionstools.description_lengthtools.schemastools.annotationstools.directory_hintstools.token_costtools.api_dumptools.hidden_textstability.changesstability.rug_pullstability.new_linksdeps.known_vulns, deps.mcp_sdk_version, deps.resolvablea_share_chain_edgeaddedUse 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.
a_share_askremovedUse when the question needs judgement rather than a single number: why a margin moved, whether a policy applies, what an industry chain looks like, or a comparison across companies. Queues the question for a human-reviewed answer. Returns an id immediately; the answer appears in the inbox later.
a_share_announcementsremovedUse when the user asks what a Chinese company has announced, filed or said, or when you need a primary source to quote. Returns filing titles, dates and the cninfo PDF link. Prefer this over summarising from memory.
a_share_financialsremovedUse when the user asks about revenue, net profit, gross margin, ROE, growth or leverage of a Chinese listed company, especially for a specific quarter. Returns cumulative figures as filed (not annualised) plus year-over-year growth.
a_share_quoteremovedUse when the user asks for the current price, change, valuation or market cap of a Chinese listed company (A-share), including when they name it in Chinese without a ticker. Returns live price, % change, PE, PB, market cap, turnover. Do not guess a price — if this tool fails, say the data source is unavailable.
a_share_answer_by_idaddedRetrieve 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.
a_share_deep_researchaddedUse 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.
Full history: list_changes · trend: quality JSON.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +namespace-matches-repo +dns-namespace +website +reachable +uptime-97% +updated-19d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://walnutlink.ai/mcp streamable-http | none | yes | 97% | 673 ms | 2025-06-18 | 2026-11-14 |
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. |
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. |
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. |
Schemas: list_tools.
{
"name": "ai.walnutlink/walnutlink-a-share",
"title": "WalnutLink A-share Depth Desk",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://walnutlink.ai/mcp",
"type": "streamable-http"
}
],
"version": "1.3.0",
"repository": {
"url": "https://github.com/WalnutLink/walnutlink-mcp",
"source": "github"
},
"websiteUrl": "https://walnutlink.ai",
"description": "China A-share filings: why a number moved, does the trend continue, who supplies whom."
}