Coinverdict

io.github.OCArk由 GitHub 帳號 OCArk 發布v1.0.0更新於 Oct 24, 2026

Free daily AI crypto research verdicts: graded stance, dimensions, and key levels for 67+ coins.

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

免費的遠端 MCP 伺服器,讓助理以唯讀方式取得 CoinVerdict 每日 AI 加密貨幣研究結論、已結算戰績與 KOL 排行榜。

可以做什麼
查詢某幣種當日結論:立場、分項評分、關鍵價位與風險,並附完整檔案連結。列出所有涵蓋的幣種代號,讓助理確認其他工具可接受的符號。查看單一幣種的已結算戰績,歷史結論會在七天後以 BTC 為基準評分。讀取全部幣種的整體結算計分板,包括勝率與未結算呼叫數。一次呼叫掃描所有涵蓋幣種的當日立場與戰績,並查看 KOL 結算排行榜。
適用情境
適合讓助理回答加密貨幣市場研究相關問題、橫向比較主流幣種的每日立場,或查核過往判斷的實際表現,而不只是看當天觀點。
執行需求
遠端 Streamable HTTP 端點;未宣告需要身分驗證、API 金鑰或環境變數。需要能連線至該端點的網路。
安裝前請注意
結論屬於研究資訊,明確不構成投資建議,不應視為交易推薦。此伺服器聲明免費且唯讀,結論每日預先產生並由快取提供;不涉及寫入操作或憑證。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Coinverdict,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.OCArk%2Fcoinverdict/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": {
    "coinverdict": {
      "type": "http",
      "url": "https://mcp.coinverdict.io/mcp"
    }
  }
}

README

CoinVerdict MCP Server

Free remote MCP server for CoinVerdict — AI crypto research verdicts, refreshed daily.

An AI analyst panel debates each major coin every day and issues a graded research verdict: stance (overweight / neutral / underweight), graded dimensions (technical · sentiment · funding · KOL consensus), key levels, and risk framing. This server gives AI assistants direct read access to today's verdicts.

Endpoint (Streamable HTTP, no auth):

https://mcp.coinverdict.io/mcp

Install

Claude Code

bash
claude mcp add --transport http coinverdict https://mcp.coinverdict.io/mcp

Cursor / other MCP clients — add a remote server with the URL above (transport: http / streamable-http).

Tools

ToolDescription
get_verdict(symbol)Today's research verdict for a coin (e.g. BTC, ETH, SOL): stance, graded dimensions (technical · sentiment · funding · KOL), key support/resistance, invalidation, risks, and a link to the full dossier.
list_coins()Every coin symbol covered by a daily verdict (100 major assets). Use it to discover which symbols the other tools accept.
get_track_record(symbol)The settled track record for a coin — CoinVerdict's differentiator. Every past daily verdict is scored 7 days later against BTC (win / loss / push). Returns the coin's W/L/P scoreboard plus recent settled calls.
get_receipts()The overall settled scoreboard across all coins: directional win rate, wins/losses/pushes, neutral count, and the settlement rule. The public accountability record.
get_market_overview()Today's verdict for all covered coins in one call — the full docket: each coin's current stance and headline.
get_kol_leaderboard()The KOL settlement leaderboard: crypto influencers ranked by their settled hit rate (from VeraMind's ledger), with sample size.

Example

"What's CoinVerdict's take on BTC today?"

The assistant calls get_verdict("BTC") and gets a compact JSON verdict with a link to the full dossier at coinverdict.io/coin/BTC.

Notes

  • Free, read-only, no API key. Verdicts are pre-generated daily and served from cache.
  • Research information, not investment advice.
  • Full dossiers (bull/bear cross-examination, risk committee ruling, KOL settlement records, charts): coinverdict.io · 中文版: coinverdict.io/zh
  • Community: Telegram channel · chat

來源:README.md,提交 f2f3d65

工具

6

get_verdict

Get today's research verdict for a coin (e.g. BTC, ETH, SOL): stance (overweight/neutral/underweight), graded dimensions (technical/sentiment/funding/KOL), key levels, and a link to the full dossier. Refreshed daily; free; not investment advice.

輸入參數symbol必填

list_coins

List every coin symbol CoinVerdict covers with a daily research verdict (100 major crypto assets: BTC, ETH, SOL, …). Use this to discover which symbols get_verdict / get_track_record accept. Returns {coins: [SYM,...], count: int, site: url}. Free, read-only.

無需輸入參數。

get_track_record

Get the SETTLED track record for a coin — CoinVerdict's differentiator. Every past daily verdict is scored 7 days later against BTC: win, loss, or push. Returns the coin's W/L/P scoreboard plus recent settled calls (date, stance, 7d-vs-BTC return, outcome). This is the receipts: misses included, never edited. Args: symbol e.g. "BTC". Free, read-only, not advice.

輸入參數symbol必填

get_receipts

Get CoinVerdict's overall settled scoreboard across all coins: directional win rate, wins/losses/pushes, neutral (no-call) count, and how many calls are still open. Every verdict is graded 7 days later against BTC. Returns {board:{winrate,W,L,P,decided,neu}, since, open_calls}. Free, read-only.

無需輸入參數。

get_market_overview

Get today's verdict for ALL covered coins in one call — the full docket: each coin's current stance (overweight/neutral/underweight), price, and W/L/P settled record. Use this to scan the whole market at once instead of calling get_verdict per coin. Returns {coins:[{symbol,stance,price_usd,board}], as_of}. Free, read-only, not advice.

無需輸入參數。

get_kol_leaderboard

Get the KOL settlement leaderboard: crypto influencers ranked by their SETTLED hit rate (from VeraMind's ledger of public calls graded after the fact — misses count). CoinVerdict-exclusive data. Returns {ranked:[{author,hit_rate_pct,n_verified,coins,n_total, n_prospective,hits_prospective,prospective_rate_pct, n_retrospective,hits_retrospective,retrospective_rate_pct}], building:[...], as_of, rule}. Rates are graded under rule kol_directional_v1: did the direction hold over a 7-day window, with a ±3% band, altcoins scored against BTC and BTC against USD — identical parameters to the settle_v1 rule CoinVerdict scores its own verdicts with. Always report the `rule` field alongside any number you quote; if it reads price_target_v1, the board fell back to price-target records and the numbers mean "did the stated price target print?" instead. Prospective (called before the fact) and backtested (graded from history) records are scored as separate lines and MUST NOT be averaged together; hit_rate_pct/n_verified are the prospective line, n_total is the combined sample size used for ranking eligibility. A null rate means no samples of that kind — report it as n=0, never as 0%. Free, read-only, not advice.

無需輸入參數。

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