MarketTrace Crypto MCP

ai.markettrace由 markettrace.ai 發布官方發布者v1.11.0更新於 Oct 24, 2026

Crypto perps for AI agents: funding, OI, liquidations, order book, CVD, volume profile, footprint.

已驗證Streamable HTTP可網頁執行資料庫金融資料與分析

概覽

AI 產生的概覽

唯讀的加密貨幣永續合約行情伺服器,讓助理取得跨交易所正規化的資金費率、未平倉量、爆倉、訂單簿與成交量資料。

可以做什麼
取得正規化市場快照,包含資金費率百分位、未平倉量、成交量、CVD、訂單簿失衡、爆倉與基差,以及資金費率百分位和近期多空爆倉金額。取得跨交易所合併的 OHLCV K 線(含每根 K 線的主動買賣差)以及封存中任一數值狀態欄位的時間序列。取得成交量分布價位(POC、價值區、未測試 POC)、大額主動成交與訂單簿掛單牆事件。查詢堆疊examined足跡失衡,以及特定條件之後的歷史前瞻報酬統計。閱讀內建說明指南,了解工具、標的、刻度與限制。
適用情境
適合助理回答有關加密永續合約持倉擁擠度、資金費率極值、爆倉流向、訂單簿結構或歷史基準機率的問題,涵蓋 Binance、Bybit、OKX 與 Hyperliquid。適用於分析與研究而非交易執行,因為它只報告歷史與事實,不做預測。
執行需求
遠端 Streamable HTTP 端點,透過電子郵件魔法連結進行 OAuth 登入,不需 API 金鑰。僅支援 stdio 的用戶端需要具備 OAuth 能力的橋接工具(例如 mcp-remote)。選用的本機橋接需要 Python 3.9+(或 Docker),呼叫工具時需提供 MARKETTRACE_BEARER 憑證。
安裝前請注意
登入透過 OAuth 電子郵件魔法連結完成,連結必須在開始登入的同一裝置與瀏覽器開啟。本機 stdio 橋接只有在設定 MARKETTRACE_BEARER 憑證後才會回傳資料,請謹慎保管該密鑰。資料僅供參考,明確不構成投資建議。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 MarketTrace Crypto MCP,將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存,絕不會在公開頁面上展示。
  3. 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/ai.markettrace%2Fagent-feed/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。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "markettrace-crypto": {
      "type": "http",
      "url": "https://api.markettrace.ai/mcp"
    }
  }
}

README

MarketTrace agent-feed

Read-only crypto perps microstructure for AI agents — normalized cross-exchange market state with self-declared coverage and freshness on every metric. Facts and normalization, no verdicts: the agent interprets.

This repo is the front door — connection configs, the interface contract, and a thin stdio bridge. The data pipeline itself (4-venue ingest, archives, normalization) is not open source.


What it serves

9 assets (BTC, ETH, SOL, BNB, XRP, DOGE, HYPE, ZEC, ENA) across Binance, Bybit, OKX, Hyperliquid:

ToolWhat it answers
get_market_stateOne normalized snapshot: funding + its trailing 2-year percentile, OI, volume, CVD, order-book imbalance, liquidations, basis, drivers. "Is ETH positioning stretched?"
get_funding_percentileCurrent funding ranked against its own trailing 2-year window (0–100) + same-sign streak.
get_liquidations_recentCross-exchange liquidation notional estimates for a window: USD, long/short split.
get_ohlcvConsolidated cross-exchange candles (5m…1d) with per-candle delta (taker buy − taker sell), for ATR, ranges, CVD and RV math.
get_conditional_outcomesMeasured forward-return history after a stated condition — base rates instead of folklore. "What happened historically after funding above the 90th percentile?"
get_state_historyTime series of any numeric state field from the 15-minute archive — the trend view behind the snapshot.
get_volume_profileVolume-profile levels per UTC day from the consolidated tape: POC, value area high/low, value-area width and its rank, a multi-day composite and naked POCs. "Is price inside yesterday's value area?"
get_big_tradesLarge aggressive orders (fills sharing venue, side and timestamp summed into one trade): per-side totals plus the biggest prints with venue, price and USD size. "Were the whale market orders buying or selling?"
get_footprint_eventsOrder-book wall events from the 1-minute footprint: absorbed and pulled walls with peak, executed and closing size in USD, plus thin-book minutes. "Were bid walls pulled before this drop?"
get_stacked_imbalancesStacked footprint imbalances from the consolidated tape: diagonal buy and sell runs per candle (1m…1h) with price band and USD size. "Where did aggressive buyers stack up on BTC this morning?"
helpA guide to the server itself: every tool grouped by the question it answers, a working example call for each, the symbols, how to read the scales, the limits, and where data without its own tool lives (open interest, CVD, funding rate). "Which tool gives me open interest?"

Data: funding rates, open interest, cumulative volume delta (CVD), order-book depth, liquidations, OHLCV candles with per-candle delta, volume-profile levels, large aggressive orders, order-book wall events, stacked footprint imbalances.

Honesty model: every metric carries a coverage entry (venues, window depth, freshness); thin history answers with disclosed depth instead of made-up numbers; conditional outcomes go history_silent below the evidence floor; every response self-declares its age. Reports history, not predictions.

Connect

Claude (web/desktop): Settings → Connectors → Add custom connector → https://api.markettrace.ai/mcp → authorize (email magic link).

Every client signs in the same way: it opens a browser, you enter your email, and a sign-in link arrives. Open it on the same device and in the same browser where you started.

Claude Code (adding the server does not sign you in, so run both):

bash
claude mcp add --transport http markettrace https://api.markettrace.ai/mcpclaude mcp login markettrace

Codex:

bash
codex mcp add markettrace --url https://api.markettrace.ai/mcpcodex mcp login markettrace

Cursor: add this to ~/.cursor/mcp.json (or use Add to Cursor on https://markettrace.ai/agents) and sign in when Cursor asks:

json
{  "mcpServers": {    "markettrace": { "url": "https://api.markettrace.ai/mcp" }  }}

Stdio-only clients (via the standard OAuth-capable bridge):

bash
npx -y mcp-remote https://api.markettrace.ai/mcp

More client configs in examples/mcp-configs.md.

Local stdio bridge (this repo)

mcp_server.py is a zero-dependency stdio bridge: it starts and answers introspection (initialize, tools/list) with no credentials — the bundled tools.json is a snapshot of the hosted server's own contract. Tool calls are proxied to the hosted endpoint when MARKETTRACE_BEARER is set; without it they return a pointer to the hosted OAuth endpoint instead of data. It holds no methodology — just a client.

Refresh the contract: tools.json is a {version, generated_at, tools} snapshot of the live server's tools/list — regenerate it by capturing that response and stamping the current contract version (mirrors feed.version in get_market_state).

bash
python3 mcp_server.py            # Python 3.9+, no dependencies

Or with Docker:

bash
docker build -t markettrace-bridge . && docker run -i markettrace-bridge

Things to ask

  • "What's the market state for BTC — is positioning stretched?"
  • "What happened historically after funding above the 90th percentile?"
  • "How did open interest build over the last 3 days?"
  • "How much got liquidated on ETH in the last hour — longs or shorts?"
  • "Where are the key volume levels on BTC — any untested POCs nearby?"
  • "Did a large resting order get absorbed on SOL in the last hour?"

Terms

Informational market data only — not financial advice. Privacy Policy · Terms of Service · Contact: [email protected]

The bridge in this repo is MIT-licensed (LICENSE); the hosted service is governed by the Terms above.

來源:README.md,提交 8d785eb

工具

0
該伺服器需要登入,因此 SourceWeft 無法在沒有帳號的情況下讀取其工具,也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

5
  1. v1.11.0最新Oct 16, 2026
  2. v1.9.0Oct 6, 2026
  3. v1.8.0Oct 6, 2026
  4. v1.6.0Sep 27, 2026
  5. v1.5.0Sep 16, 2026

評分

已滿足適用檢查項的 85%

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15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分