market-data

Verified market data for AI trading agents: quality-flagged candles, funding, OI, order flow. x402.

我該用這個嗎

品質與安全性

A
說明品質
89%
結構描述完整度
71%
命名品質
97%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

發現項目(6)

  • LOWTool 'describe_catalog' description lacks action verb在 describe_catalog 中
  • LOWTool 'get_bars' description lacks action verb在 get_bars 中
  • LOWTool 'get_regime_label' description lacks action verb在 get_regime_label 中
  • LOWTool 'get_context' description lacks action verb在 get_context 中
  • LOWTool 'get_events' description lacks action verb在 get_events 中
  • LOWTool 'get_insider' description lacks action verb在 get_insider 中

根據工具定義與協定合規性的自動化分析。

上下文成本

~1,964Token(工具定義)
~448 B典型回應大小
中等的注意力影響(128k 上下文的 1.53%)

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": {
    "market-data": {
      "url": "https://iturri.ai/mcp"
    }
  }
}

遠端端點

https://iturri.ai/mcpstreamable-http

它能做什麼

工具清單

工具(22)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢describe_catalog

Free discovery: symbols, timeframes, ranges, pricing, quality legend.

輸入結構描述

{
  "type": "object",
  "properties": {}
}
🟢get_bars(symbol, tf, start, end)

Quality-flagged OHLCV candles. Priced per 1,000 candles.

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string"
    },
    "tf": {
      "type": "string"
    },
    "start": {
      "type": "string"
    },
    "end": {
      "type": "string"
    }
  },
  "required": [
    "symbol",
    "tf"
  ]
}
🟢get_features(symbol, tf, start, end)

Documented leakage-safe feature matrix rows. Priced per call.

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string"
    },
    "tf": {
      "type": "string"
    },
    "start": {
      "type": "string"
    },
    "end": {
      "type": "string"
    }
  },
  "required": [
    "symbol",
    "tf"
  ]
}
⚪build_bundle(pack, symbol, tf)

Signed URL for a dataset SKU. Packs: crypto|equities ($59 each), everything ($149: both packs + all token sequences, $730 list), tokens ($18/symbol), dataset (per-symbol OHLCV, crypto $14 / equity $5), mtf (aligned multi-timeframe bundle $9, crypto only), features (feature matrix, crypto $7 / equity $4). Priced as the SKU.

輸入結構描述

{
  "type": "object",
  "properties": {
    "pack": {
      "type": "string",
      "enum": [
        "crypto",
        "equities",
        "tokens",
        "dataset",
        "mtf",
        "features",
        "everything"
      ]
    },
    "symbol": {
      "type": "string",
      "description": "required for tokens|dataset|mtf|features"
    },
    "tf": {
      "type": "string",
      "description": "features only — crypto: 1h (default) or 15m; equity: 1d"
    }
  },
  "required": [
    "pack"
  ]
}
🟢get_regime_label(symbol, timestamp)

Descriptive market-state label (trend/range × calm/vol quadrant) for the most recent completed bar at or before a timestamp. Not a prediction.

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string"
    },
    "timestamp": {
      "type": "string"
    }
  },
  "required": [
    "symbol",
    "timestamp"
  ]
}
🟢get_funding(symbol, start, end)

Perp funding-rate settlement history from listing date (checksummed archive).

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string"
    },
    "start": {
      "type": "string"
    },
    "end": {
      "type": "string"
    }
  },
  "required": [
    "symbol"
  ]
}
🟢get_open_interest(symbol, tf, start, end)

Open interest with per-row quality flags (verified archive + flagged bridge). tf=1h (default, full history) or tf=5m (archive-native 5-minute rows from 2020-09; ranged pulls, ~100k rows max per call).

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string"
    },
    "tf": {
      "type": "string",
      "enum": [
        "1h",
        "5m"
      ]
    },
    "start": {
      "type": "string"
    },
    "end": {
      "type": "string"
    }
  },
  "required": [
    "symbol"
  ]
}
🟢get_long_short(symbol, start, end)

Positioning ratios at 5-minute cadence from the checksummed venue archive (2020-09+): top-trader long/short by accounts and by position size, all-accounts long/short, taker buy/sell volume ratio. Ranged pulls, ~100k rows max per call.

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string"
    },
    "start": {
      "type": "string"
    },
    "end": {
      "type": "string"
    }
  },
  "required": [
    "symbol"
  ]
}
🟢get_context(series, start, end)

Context series: fear_greed_1d, VIX_1d, DXY_1d, TNX_1d, DJI_1d.

輸入結構描述

{
  "type": "object",
  "properties": {
    "series": {
      "type": "string"
    },
    "start": {
      "type": "string"
    },
    "end": {
      "type": "string"
    }
  },
  "required": [
    "series"
  ]
}
🟢get_events(type, start, end)

Curated macro/crypto events (FOMC w/ surprise, halvings, incidents) in a range.

輸入結構描述

{
  "type": "object",
  "properties": {
    "type": {
      "type": "string"
    },
    "start": {
      "type": "string"
    },
    "end": {
      "type": "string"
    }
  }
}
🟢get_orderflow(symbol, tf, start, end)

Taker buy/sell imbalance, trade counts, quote volume (1h/1d via API; denser tiers in packs). buy_ratio 0.5 = balanced.

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string"
    },
    "tf": {
      "type": "string",
      "enum": [
        "1h",
        "1d"
      ]
    },
    "start": {
      "type": "string"
    },
    "end": {
      "type": "string"
    }
  },
  "required": [
    "symbol"
  ]
}
⚪validate_backtest_data(symbol, tf, start, end)

Quality report for a dataset spec before you backtest on it: coverage, per-bar quality distribution, gaps, and concrete warnings.

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string"
    },
    "tf": {
      "type": "string"
    },
    "start": {
      "type": "string"
    },
    "end": {
      "type": "string"
    }
  },
  "required": [
    "symbol",
    "tf"
  ]
}
🟡audit_my_data(symbol, tf, bars)

FREE: submit YOUR OHLCV bars and get an accuracy verdict against the verified archive — score, worst windows, systematic-offset findings. Tells you what's wrong, not the corrected values (that's get_bars).

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string"
    },
    "tf": {
      "type": "string"
    },
    "bars": {
      "type": "object",
      "description": "columnar arrays: t (epoch s or ISO) required; o/h/l/c optional",
      "properties": {
        "t": {
          "type": "array"
        },
        "o": {
          "type": "array"
        },
        "h": {
          "type": "array"
        },
        "l": {
          "type": "array"
        },
        "c": {
          "type": "array"
        }
      }
    }
  },
  "required": [
    "symbol",
    "tf",
    "bars"
  ]
}
🟡lookahead_check(symbol, tf, signals)

FREE: submit backtest signals ({t, price}) and get an execution-feasibility verdict — impossible fills outside the bar's traded range, fills pinned at bar extremes (classic lookahead bias).

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string"
    },
    "tf": {
      "type": "string"
    },
    "signals": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "t": {},
          "price": {
            "type": "number"
          },
          "side": {
            "type": "string"
          }
        }
      }
    }
  },
  "required": [
    "symbol",
    "tf",
    "signals"
  ]
}
🟡survivorship_check(symbols, start, end, asset)

FREE: submit a backtest universe + window and get a survivorship-bias verdict — which of your symbols died mid-window, and which delisted symbols we cover that your universe omits.

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbols": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "start": {
      "type": "string"
    },
    "end": {
      "type": "string"
    },
    "asset": {
      "type": "string",
      "enum": [
        "crypto",
        "equity"
      ]
    }
  },
  "required": [
    "symbols"
  ]
}
🟢get_fundamentals(symbol, concept, start, end, as_of)

Point-in-time SEC XBRL fundamentals (80 filers, incl. delisted): every restatement vintage with its filed date. Pass as_of for what was knowable then. Filter by concept (e.g. Assets, Revenues).

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string"
    },
    "concept": {
      "type": "string"
    },
    "start": {
      "type": "string"
    },
    "end": {
      "type": "string"
    },
    "as_of": {
      "type": "string"
    }
  },
  "required": [
    "symbol"
  ]
}
🟡get_insider(symbol, start, end)

SEC Form 4 insider transactions as filed (80 symbols, since 2016): officer/director trades with shares, price, post-trade holdings.

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string"
    },
    "start": {
      "type": "string"
    },
    "end": {
      "type": "string"
    }
  },
  "required": [
    "symbol"
  ]
}
🟢get_institutional(symbol, start, end)

Quarterly 13F institutional aggregates (81 symbols): holders, shares, value + QoQ deltas from SEC DERA structured tables.

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string"
    },
    "start": {
      "type": "string"
    },
    "end": {
      "type": "string"
    }
  },
  "required": [
    "symbol"
  ]
}
🟢get_funding_spread(symbol, start, end)

Hourly CEX-vs-DEX funding spread (67 symbols): Hyperliquid funding vs Binance 1h-equivalent, from HL genesis 2023-05.

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string"
    },
    "start": {
      "type": "string"
    },
    "end": {
      "type": "string"
    }
  },
  "required": [
    "symbol"
  ]
}
🟢get_market_pulse

FREE daily pulse across the catalog: regime flips, funding extremes, CEX-vs-DEX spread extremes, biggest daily moves. One day of values — the history behind each number is the priced product.

輸入結構描述

{
  "type": "object",
  "properties": {}
}
🟢get_whats_new

FREE: what the daily refresh changed — dataset windows extended vs ~7 days ago, new symbols and sections, freshness per asset class.

輸入結構描述

{
  "type": "object",
  "properties": {}
}
🟢get_quality_receipts

FREE public scoreboard: last 30 daily fresh-data audits (cross-venue in-band vs Coinbase, 1m->1h rebuild exactness, depth sanity) — failures included, not hidden.

輸入結構描述

{
  "type": "object",
  "properties": {}
}

建議的提示詞

retrieve_data
Get details about [item] from market-data
預期的工具: get_bars
fetch_info
Fetch [information type] using market-data
預期的工具: get_bars

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本22 個工具
已驗證未記錄版本22 個工具