signaldaemon
Narrative & signal intelligence for AI agents: crypto/AI/macro convergence & divergence.
我該用這個嗎
品質與安全性
發現項目（1）
- LOWTool 'get_market_narratives' description lacks action verb在 get_market_narratives 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": {
"signaldaemon": {
"url": "https://api.signaldaemon.com/mcp"
}
}
}遠端端點
https://api.signaldaemon.com/mcpstreamable-http它能做什麼
工具清單
工具（3）
🟢get_market_narratives(limit)
Return top crypto market narratives with strength, momentum, and price divergence signals.
輸入結構描述
{
"type": "object",
"properties": {
"limit": {
"default": 8,
"title": "Limit",
"type": "integer"
}
},
"title": "get_market_narrativesArguments"
}🟢vet_trade(symbol, side, horizon, source)
Before placing a trade, check whether the crypto/AI/macro NARRATIVE layer supports, cautions, or contradicts it. Returns a stance (support|caution|contradict|no_signal) with reason + confidence. Read-only, NOT a trade recommendation — it vets YOUR candidate trade against cross-source narrative convergence and capital-vs-narrative divergence, and abstains (no_signal) when there is no narrative coverage. Call it as a second opinion after your own strategy/TA has a candidate {symbol, side}.
輸入結構描述
{
"type": "object",
"properties": {
"symbol": {
"title": "Symbol",
"type": "string"
},
"side": {
"title": "Side",
"type": "string"
},
"horizon": {
"default": null,
"title": "Horizon",
"type": "string"
},
"source": {
"default": null,
"title": "Source",
"type": "string"
}
},
"required": [
"symbol",
"side"
],
"title": "vet_tradeArguments"
}🟢get_clean_feed(query, category, limit)
Return a curated clean feed of articles for a given query topic.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"category": {
"default": null,
"title": "Category",
"type": "string"
},
"limit": {
"default": 8,
"title": "Limit",
"type": "integer"
}
},
"required": [
"query"
],
"title": "get_clean_feedArguments"
}社群
證據