Insider Radar

io.github.mypocketsmells由 GitHub 帳號 mypocketsmells 發布v1.1.0更新於 Oct 27, 2026

Lab telemetry market: 25 x402 USDC-paid tools — leaderboard, KOL signals, outcomes, more.

已驗證Streamable HTTP可網頁執行金融資料與分析

概覽

AI 產生的概覽

遠端 MCP 伺服器,提供某模擬交易研究實驗室的遙測資料:機器人排行榜、KOL 訊號、內部人申報與市場資料,多數工具按次付費。

可以做什麼
  • 查詢服務狀態、快照新鮮度以及附單次價格的產品目錄
  • 讀取全艦隊競技場彙總、機器人排行榜、每日損益帳本與 alpha 追蹤淨值歷史
  • 取得訊號流、告警、校準、跨平台機率分歧、擁擠度與最佳化器決策
  • 查詢迷因幣 KOL 資料:即時與延遲合流訊號、錢包績效統計、創建者索引、熱度指標與可跟單評級
  • 檢視 SEC Form 4 內部人買進、10b5-1 計畫辨識、13F 持股、國會 PTR 交易及與申報連結的證據叢集
  • 取得合併研究包與已記錄的 Kalshi SOL 訂單簿深度
適用情境
適合讓助理彙總或比較模擬交易實驗室指標、迷因幣錢包訊號,或公開的內部人與國會申報資料,而不必自建資料管線。可先用免費的狀態與競技場預覽呼叫確認資料新鮮度,再決定是否付費。
執行需求
遠端 streamable HTTP 端點;未宣告本機執行環境、帳號或 API 金鑰。多數工具透過 x402 以 USDC 按次付費,除免費的狀態與預覽呼叫外,需要錢包或支援付款的用戶端。需能連線至託管端點。
安裝前請注意
多數工具每次呼叫需支付 USDC,呼叫前請透過狀態工具查看價格。所有數字皆為研究實驗室的模擬紙上美元,不構成投資建議,也非實盤交易;在考量有效下注次數前,排名報酬被描述為主要由運氣驅動。部分工具涉及錢包層級與內部人資料,輸出應視為研究訊號而非交易指令。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Insider Radar,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.mypocketsmells%2Finsider-radar/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": {
    "insider-radar": {
      "type": "http",
      "url": "https://insider-radar-agent.insider-radar-agent.workers.dev/mcp"
    }
  }
}

工具

27

radar_status

Service status: snapshot freshness, product catalog with per-call prices, and the honesty disclaimer. Free.

無需輸入參數。

arena

Fleet-wide arena summary of the paper-trading lab (bot counts, venues, aggregate equity). Free teaser.

無需輸入參數。

leaderboard

Ranked bot leaderboard with eff_n and the luck-ceiling honesty note. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

signals

Current signal feed headlines from the lab's signal bus. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

alerts

Recent lab alerts (drawdowns, retirements, anomalies). Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

calibration

Forecast calibration by venue/category — predicted vs realized. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

divergences

Cross-venue probability divergences (e.g. Kalshi vs Polymarket gaps). Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

crowding

Exposure crowding: where the fleet's directional risk is concentrated. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

optimizer

Optimizer status and recent parameter decisions. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

creators

Pump.fun deployer index built forward by our launch listener: 900+ creator wallets with launch histories, venue-aware rug counts, first/last seen. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

kol_stats

Per-wallet outcome statistics for ~300 tracked memecoin KOL wallets — our computed win rates and PnL distributions over observed trades. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

alpha_track

Daily equity/PnL histories for the lab's edge-protected bots under stable anonymous handles — real performance, withheld identities; track any handle across snapshots. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

sol_depth

Recorded Kalshi SOL-market L2 depth (top-5 levels per side), previous-day and older only (T+1) — we recorded it live; Kalshi publishes no historical depth. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

kol_signals_live

Live KOL confluence buy/exit signals (≤15 min old): distinct human buyers, strength, rug-risk callouts, momentum — the actionable tier. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

kol_outcomes

Forward-marked signal outcomes WITH a matched control arm: rug rates, checkpoint returns (15m/1h/6h/24h) by risk level and confluence — honesty-graded. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

snipe_outcomes

Launch-snipe paper ledger with a randomized control arm: detect latency, entry efficiency, checkpoint marks per snipe. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

wire_clusters

Cross-source evidence clusters joining price anomalies to specific SEC filings (Form 4 accessions, URLs) — graded, windowed, cited. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

solscout_verdicts

Copy-gradeability verdicts for Solana memecoin wallets: composite scores, consistency, retirement calls (candidate lists withheld). Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

insider_plans

10b5-1 plan detection per insider filing — was the buy pre-scheduled? Per-accession tags plus aggregate plan rates. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

research_pack

Seven research panels in one call: family correlation + effective-n, edge calibration, insider event study, regime joins, econ calendar, weekly digest, daily alpha cards. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

kol_events

Narrated detector event stream: meta-signals, distribution flips, known-rugger callouts (last 2000 events). Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

fleet_ledger

Fleet-wide daily P&L ledger: totals, venue splits, per-day rows, tape reconciliation — the transparency companion to alpha_track. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

kol_signals_delayed

Same KOL confluence feed as kol_signals_live with every row at least 45 minutes old — the evaluation tier. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

kol_froth

Memecoin froth gauge, current level plus full history: human buys/hour, danger share, distribution events, percentile. Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

smart_holdings

13F institutional holdings rollup: top-held names, filer roster, per-ticker holder counts (top 300). Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

insider_tape

Parsed SEC Form-4 insider buys, newest first: roles, titles, shares, price, value, disclosure lag (last 1000). Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

congress_tape

Parsed House/Senate PTR trades: member, ticker, type, amounts, filing lag (last 1000). Paper-trading lab telemetry; All figures are simulated paper dollars from a research lab — not investment advice, not live trading, no real positions. Ranked returns are dominated by luck until effective bet counts (eff_n), calibration and crowding say otherwise.

無需輸入參數。

版本歷史

1
  1. v1.1.0最新Sep 16, 2026

評分

已滿足適用檢查項的 83%

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

    請宣告包含 README 的 GitHub 儲存庫,或在 OAuth 受保護資源後設資料中提供 resource_documentation。

  • 授權條款不適用

    託管服務按其提供方的條款使用,因此這裡不要求授權條款。此檢查項不計入百分比。