Signaldaemon

io.github.bevanding由 GitHub 帳號 bevanding 發布v1.0.0更新於 Oct 25, 2026

Narrative & signal intelligence for AI agents: crypto/AI/macro convergence & divergence.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取金融

概覽

AI 產生的概覽

遠端 MCP 伺服器，為助理提供精選的加密、AI 與宏觀市場敘事，並對擬議交易做敘事層檢核。

可以做什麼
依指定數量取得排序後的市場敘事，含強度、動能與價格背離訊號。依主題查詢取得精選的乾淨文章流，可附加分類。對候選交易做敘事層檢核，回傳支持、謹慎、矛盾或無訊號的態度，並附理由與信心度。三個工具皆標示為唯讀，且在無涵蓋時如實說明而非憑空生成。
適用情境
適合需要加密、AI 與宏觀主題敘事層背景的助理，或想在送出交易前判斷其是否符合當前敘事。它不是價格或行情資料來源，也不是原始新聞流。
執行需求
遠端 Streamable HTTP 端點；需在 x-api-key 標頭中提供 API 金鑰，可自助申請、無需註冊。不支援遠端 MCP 的用戶端可用本機 stdio 橋接，需 Python 與 mcp 套件及 SIGNALDAEMON_API_KEY 環境變數，或使用 Docker。工具呼叫需要金鑰，工具清單查詢無需金鑰。
安裝前請注意
API 金鑰屬於憑證，應妥善保管；橋接程式從 SIGNALDAEMON_API_KEY 讀取。vet_trade 僅檢核候選交易，明確不是交易建議，交易決策仍由使用者負責。查詢內容與交易細節會傳送給第三方託管服務，其處理流程並非開源。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Signaldaemon，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/io.github.bevanding%2Fsignaldaemon/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": {
    "signaldaemon": {
      "type": "http",
      "url": "https://api.signaldaemon.com/mcp"
    }
  }
}

README

signaldaemon

Narrative & signal intelligence for AI agents — crypto, AI, and macro. A dumb-but-trustworthy pipe: it delivers curated narrative & signal, not raw data, and it fails safe — when it has no coverage it says so, rather than inventing. Built for machines, not human eyes.

This repo is the front door — quickstart, client configs, and the interface contract. The pipeline itself (sources, scoring, curation) is not open source.

What it is (and isn't)

It isIt is not
Cross-source narrative convergence + capital-vs-narrative divergenceA price/market-data API (use CoinGecko etc. for that)
Coverage across ~14 crypto/AI/macro domainsA raw news firehose
Fails safe — "no coverage" over hallucinationA database you query for facts
For agents (API/MCP), token-cost-agnostic, quality-firstA human-facing dashboard

Quickstart

bash
# 1 · self-serve a demo key (no signup)KEY=$(curl -s -X POST https://api.signaldaemon.com/v1/request-key | jq -r .key)
# 2 · the day's ranked narratives + derived signals (cached, instant)curl -s https://api.signaldaemon.com/v1/narratives \  -H "x-api-key: $KEY" -d '{"limit":8}'
# 3 · clean narrative feed for a topiccurl -s https://api.signaldaemon.com/v1/feed \  -H "x-api-key: $KEY" -d '{"query":"restaking","limit":8}'

Connect from your agent (MCP)

Remote MCP over Streamable HTTP, authenticated with the x-api-key header.

bash
# Claude Codeclaude mcp add --transport http signaldaemon \  https://api.signaldaemon.com/mcp --header "x-api-key: <KEY>"
yaml
# Hermes Agent — ~/.hermes/config.yamlmcp_servers:  signaldaemon:    url: "https://api.signaldaemon.com/mcp"    headers: { x-api-key: "<KEY>" }

More clients (Cursor, Cline) in examples/mcp-configs.md. Tools: get_market_narratives(limit) · get_clean_feed(query, category, limit) · vet_trade(symbol, side) — all annotated readOnlyHint. vet_trade is the pre-trade gate: hand it a candidate trade and it returns a narrative-layer stance (support/caution/contradict/no_signal) with reason + confidence — it vets, it does not recommend.

Local stdio bridge

For clients that don't support remote MCP, this repo ships a thin stdio bridge (mcp_server.py) exposing the same three tools over the hosted API. It holds no methodology — just a client.

bash
pip install mcpexport SIGNALDAEMON_API_KEY=cns_...   # https://signaldaemon.com/consolepython mcp_server.py

Or with Docker:

bash
docker build -t signaldaemon-mcp . && \docker run -i -e SIGNALDAEMON_API_KEY=cns_... signaldaemon-mcp

The bridge starts and answers introspection (tools/list) without a key; tool calls require one.

Interface

Endpoints and response-field contract (incl. the divergence schema) in API.md. Field names are stable.

License

Examples and docs in this repo: MIT (see LICENSE). The signaldaemon service and pipeline are proprietary.

來源：README.md，提交 7f5a8d7

工具

3

get_market_narratives

Return top crypto market narratives with strength, momentum, and price divergence signals.

輸入參數limit

vet_trade

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}.

輸入參數side必填sourcesymbol必填horizon

get_clean_feed

Return a curated clean feed of articles for a given query topic.

輸入參數limitquery必填category

版本歷史

1
  1. v1.0.0最新Sep 16, 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