ClearMarket

Reference data for prediction markets: graded resolution clarity, cross-venue links, provenance.

我該用這個嗎

品質與安全性

A
說明品質
97%
結構描述完整度
87%
命名品質
100%
汙染風險
80%
權限相符程度
100%
協定合規性
100%

發現項目(3)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool 'get_market' description contains placeholder text在 get_market 中
  • INFOTool description contains placeholder or incomplete text在 get_market 中

根據工具定義與協定合規性的自動化分析。

上下文成本

~1,551Token(工具定義)
~1.0 KB典型回應大小
中等的注意力影響(128k 上下文的 1.21%)

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": {
    "clearmarket": {
      "url": "https://api.clearmarket.fyi/mcp"
    }
  }
}

遠端端點

https://api.clearmarket.fyi/mcpstreamable-http

它能做什麼

工具清單

工具(6)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢list_events(q, category, platform, grade, limit, ...)

Browse or search ClearMarket prediction-market events. Filter by category, platform, Resolution Clarity Grade, or free-text `q`. `q` is token-AND across question + tags, so SHORT KEYWORD queries match best ("microstrategy bitcoin", "fed rate") — natural-language phrases often return nothing. Returns compact graded summaries: slug, question, venues_covered, primary grade, rcg_score (0-100, for ranking clarity), last_price, and status (open / resolved). Start here when you have a topic but not a slug; then call get_event for the full graded record. Categories: economics, financials, crypto, companies, technology, politics, geopolitics, health, climate.

輸入結構描述

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free-text search across event questions. Omit to list the whole filtered universe."
    },
    "category": {
      "type": "string",
      "enum": [
        "economics",
        "financials",
        "crypto",
        "companies",
        "technology",
        "politics",
        "geopolitics",
        "health",
        "climate"
      ]
    },
    "platform": {
      "type": "string",
      "enum": [
        "kalshi",
        "polymarket"
      ]
    },
    "grade": {
      "type": "string",
      "enum": [
        "A",
        "B",
        "C"
      ],
      "description": "Resolution Clarity Grade of the primary market."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 50
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "default": 0
    }
  }
}
🟡get_event(slug, detail)

Fetch the full ClearMarket record for one event by slug: the canonical question, every market in this event's single-venue bundle, each market's current price + Resolution Clarity Grade (A/B/C) + resolution-source provenance, the canonical question_id where the question is linked across venues/events (null otherwise; also_on lists the same question priced on the other venue, when it trades there), and the upcoming catalyst dates that move it before it resolves. In the default detail="full", each market in the bundle is FULLY detailed (grade, rcg.caps, provenance, direction, settlement_style, also_on) — you do not need a separate get_market call for markets already in this event. Note: a shared question_id means same topic across venues; in rare cases it links structurally-different contracts (e.g. a "hike" vs a "cut-count" market), so verify the contract shape before treating two as an arbitrage pair. Use when you need the authoritative, graded view of a SPECIFIC event — including its cross-venue twins via also_on — before reasoning about or acting on a prediction market. If you only have a topic (not a slug), call list_events first. Set detail="concise" for a quick grade/price/source check (each market trimmed to the essentials — much smaller for events with many markets); use the default detail="full" when you need every market's rules, contract shape, and complete provenance.

輸入結構描述

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Event slug (e.g. \"kxgdpyear-26\") or CM event id (CM-EVT-…)."
    },
    "detail": {
      "type": "string",
      "enum": [
        "concise",
        "full"
      ],
      "default": "full",
      "description": "concise = essentials only (grade, price, source, also_on per market); full = the complete record. Default full."
    }
  },
  "required": [
    "slug"
  ]
}
🟢get_market(market_id)

Fetch one market and judge whether its price can be trusted. Accepts whatever id you have: a ClearMarket id (CM-MKT-…), a venue-native market id or Kalshi ticker, or a market URL (best-effort — Kalshi tickers / a native id in the path resolve; for Polymarket pass the conditionId, not the slug URL). Returns: raw question, current price / implied probability, the Resolution Clarity Grade with rcg.score (0-100) and rcg.caps (a cap such as "uncommitted_placeholder" hard-limits the grade — that is why a single-source market can still be C), full resolution provenance (arbitration_model = who resolves it, named source, source_type, and a graded source_status on EVERY market: named / no-committed-source / none / unknown), the contract shape (direction, settlement_style, threshold), the canonical question_id where linked, and also_on (the same question priced on other venues). The returned market_id is ALWAYS the canonical ClearMarket id (CM-MKT-…) — store and reuse THAT, not the venue id. Use before trusting or acting on a price.

輸入結構描述

{
  "type": "object",
  "properties": {
    "market_id": {
      "type": "string",
      "description": "A ClearMarket id (CM-MKT-…), a venue-native market id / Kalshi ticker, or a market URL (best-effort: Kalshi URLs resolve; for Polymarket pass the conditionId)."
    }
  },
  "required": [
    "market_id"
  ]
}
🟢list_upcoming_catalysts(days)

List scheduled catalysts (CPI, jobs, FOMC, GDP, large-cap earnings) in the next N days that move prediction-market prices BEFORE those markets resolve — a cross-event view across the whole calendar. Each entry is provenanced to its authoritative source (BLS, Fed, etc.). Use to find what scheduled events will reprice the prediction-market universe soon.

輸入結構描述

{
  "type": "object",
  "properties": {
    "days": {
      "type": "integer",
      "minimum": 1,
      "maximum": 365,
      "default": 30
    }
  }
}
🟢list_signals(event_id, category, venue, detection_path, limit)

Browse the CM Signal daily wire — short, structured prediction-market bulletins (the price is the lede, news is context). Filter by event_id (every wire touching a specific event), category, venue, or detection type (news_cycle, cross_venue_divergence, benchmark_drift, volume_spike). Returns compact records, newest first; call get_signal for the full bulletin. Use to find ClearMarket's editorial read on what is moving.

輸入結構描述

{
  "type": "object",
  "properties": {
    "event_id": {
      "type": "string",
      "description": "Return only wires that target or link to this CM event_id."
    },
    "category": {
      "type": "string",
      "description": "Signal category tag (case-insensitive): VS_BENCHMARK_DRIFT | CROSS_VENUE_DIVERGENCE | VOLUME_SPIKE | MOMENTUM_REPRICING | PRE_EVENT_PRICING. For thematic filtering use list_events."
    },
    "venue": {
      "type": "string",
      "enum": [
        "kalshi",
        "polymarket"
      ]
    },
    "detection_path": {
      "type": "string",
      "enum": [
        "news_cycle",
        "cross_venue_divergence",
        "benchmark_drift",
        "volume_spike"
      ]
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 30
    }
  }
}
🟢get_signal(slug)

Fetch one full CM Signal wire by slug: headline, the 3-5 structured bullets, atomic claims with per-field provenance tiers, the target + linked events, primary and related markets with prices, and sources. Use when you have a wire slug (from list_signals) and need the complete bulletin with its proof chain.

輸入結構描述

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Wire slug, e.g. \"us-iran-nuclear-deal-before-2027-polymarket-77-2026-05-29\"."
    }
  },
  "required": [
    "slug"
  ]
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本6 個工具
已驗證未記錄版本6 個工具
已驗證未記錄版本6 個工具