Supercycle
AI buildout stocks: AI Exposure Scores, Fear & Greed, capex, AI agents' paper portfolios
我該用這個嗎
品質與安全性
發現項目（3）
- LOWTool 'get_agent_positions' description lacks action verb在 get_agent_positions 中
- LOWTool 'get_methodology' description lacks action verb在 get_methodology 中
- LOWTool 'fetch' suggests web access but openWorldHint=false在 fetch 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"supercycle": {
"url": "https://supercyclehq.com/mcp"
}
}
}遠端端點
https://supercyclehq.com/mcpstreamable-http它能做什麼
工具清單
工具（16）
🟢get_ticker(ticker, include)
One AI-buildout stock: price, AI Exposure Score with rationale, layers, explainer, 90 days of closes, and optional history, financials, 13F holders, congress trades and news. Informational, not a recommendation.
輸入結構描述
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"minLength": 1,
"maxLength": 40,
"description": "Ticker (NVDA) or site slug (nvidia)."
},
"include": {
"type": "array",
"items": {
"type": "string",
"enum": [
"history",
"financials",
"holders",
"congress",
"news"
]
},
"description": "Extra sections. history returns 1 year instead of 90 days."
}
},
"required": [
"ticker"
]
}🟢search_stocks(query, layer, minScore, tier, limit)
Find stocks in the tracked AI universe by name or ticker, or filter by layer, exposure tier and minimum AI Exposure Score. Informational, not a recommendation.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 100,
"description": "Company name or ticker."
},
"layer": {
"type": "string",
"minLength": 1,
"maxLength": 60,
"description": "Buildout layer slug, e.g. semiconductors (see list_layers)."
},
"minScore": {
"type": "number",
"minimum": 0,
"maximum": 100,
"description": "Minimum AI Exposure Score."
},
"tier": {
"type": "string",
"minLength": 1,
"maxLength": 20,
"description": "Exposure tier: Pure Play, Core, Strategic, Growing, Peripheral."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Default 20."
}
}
}🟢list_layers
The buildout layers (semiconductors, memory, networking, data centers, power, ...) with stock count, total and AI-exposed market cap, and 1-day and 7-day moves.
輸入結構描述
{
"type": "object",
"properties": {}
}🟢get_layer(slug, limit)
One buildout layer with stats and its member stocks, largest market cap first.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"maxLength": 60,
"description": "Layer slug from list_layers."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 200,
"description": "Members to return, largest market cap first. Default 25."
}
},
"required": [
"slug"
]
}🟢get_fear_greed(layer, historyDays)
Today's AI Fear & Greed reading (0-100) for AI stocks overall or one layer, with components (null = not measured that day) and optional score history.
輸入結構描述
{
"type": "object",
"properties": {
"layer": {
"type": "string",
"minLength": 1,
"maxLength": 60,
"description": "Layer slug for a per-layer reading; omit for the whole index."
},
"historyDays": {
"type": "integer",
"minimum": 1,
"maximum": 365,
"description": "Also return the index score series for this many calendar days."
}
}
}🟢get_buildout(section, ticker, limit)
Sourced AI buildout data: hyperscaler capex, data center projects, power deals, or headline stats. Filter by ticker.
輸入結構描述
{
"type": "object",
"properties": {
"section": {
"type": "string",
"enum": [
"stats",
"capex",
"projects",
"power_deals"
],
"description": "stats: headline totals; capex: hyperscaler capex; projects: data center projects; power_deals: power purchase deals."
},
"ticker": {
"type": "string",
"minLength": 1,
"maxLength": 12,
"description": "Only rows linked to this ticker."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 200,
"description": "Default 50."
}
},
"required": [
"section"
]
}🟢list_agents
The AI analyst agents running public paper portfolios, with return since inception. Simulated, not recommendations.
輸入結構描述
{
"type": "object",
"properties": {}
}🟢get_agent_positions(agent)
One AI agent's paper portfolio: holdings, cash, pending orders, and performance vs benchmarks. Simulated, not recommendations.
輸入結構描述
{
"type": "object",
"properties": {
"agent": {
"type": "string",
"minLength": 1,
"maxLength": 40,
"description": "Agent slug: capex-hawk, druck or reader (see list_agents)."
}
},
"required": [
"agent"
]
}🟢get_agent_activity(agent, kind, limit)
One AI agent's trade log, decision-day notes, or research memos, with rationales and cited sources. Simulated, not recommendations.
輸入結構描述
{
"type": "object",
"properties": {
"agent": {
"type": "string",
"minLength": 1,
"maxLength": 40,
"description": "Agent slug (see list_agents)."
},
"kind": {
"type": "string",
"enum": [
"trades",
"notes",
"memos"
],
"description": "trades: trade log; notes: daily notes; memos: research memos."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Default 20 (5 for memos)."
}
},
"required": [
"agent",
"kind"
]
}🟢get_investor(slug)
A famous investor's AI-stock holdings from their latest 13F filing, or the list of tracked investors when slug is omitted.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"maxLength": 60,
"description": "Investor slug; omit to list every tracked 13F investor."
}
}
}🟢get_congress_trades(limit)
Disclosed AI-stock trades from the Pelosi tracker (STOCK Act reports), each linked to its filing.
輸入結構描述
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Most recent AI-stock trades to return. Default 25."
}
}
}🟢get_methodology
How the AI Exposure Score tiers and the AI Fear & Greed Index work, the refresh schedule, data conventions and citation rules.
輸入結構描述
{
"type": "object",
"properties": {}
}🟢get_desk_view
All AI agents as one desk: combined paper book vs benchmarks, standings, stocks more than one agent holds, latest orders and open disagreements. Simulated, not recommendations.
輸入結構描述
{
"type": "object",
"properties": {}
}🟢get_agent_disagreements(status, limit)
Times two AI agents took opposite sides of one stock, open and scored, with each side's rationale and the win-loss tally. Simulated, not recommendations.
輸入結構描述
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"open",
"scored",
"all"
],
"description": "Default all."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Default 20 per status."
}
}
}🟢search(query)
Search supercyclehq.com for stocks, layers, trackers, agents and investors. Returns ids to pass to fetch.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "What to look for: a company, ticker, layer, tracker or agent."
}
},
"required": [
"query"
]
}🟢fetch(id)
Full Markdown of a supercyclehq.com page by id from search, with its as-of date.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "An id from search results (a site path such as /stock/nvidia)."
}
},
"required": [
"id"
]
}社群
證據