Skip to main content
Glama
Rekko MCP
by Rekko-AI

rekko-mcp

rekko-mcp MCP server MCP Badge

面向 AI 编程助手的预测市场情报。提供 24 个 MCP 工具,用于跨 Kalshi、Polymarket、Robinhood 和 Coinbase 进行市场数据、深度分析、交易信号、套利检测和筛选。

安装

uvx rekko-mcp
# or
pip install rekko-mcp

需要 Python 3.11+ 和 Rekko API 密钥(提供免费层级)。

Related MCP server: telekash-mcp-server

配置

Claude Code:

claude plugin install rekko

或者添加到 .mcp.json:

{
  "mcpServers": {
    "rekko": {
      "command": "uvx",
      "args": ["rekko-mcp"],
      "env": { "REKKO_API_KEY": "rk_free_your_key_here" }
    }
  }
}

Cursor — 在 .cursor/mcp.json 中使用相同的 .mcp.json 格式。

你将获得

  • 市场数据 — 浏览、搜索并获取 Kalshi、Polymarket、Robinhood 和 Coinbase 的价格历史记录

  • 深度分析 — 包含概率估计和因果分解的多阶段 AI 研究流水线(30-90秒)

  • 交易信号 — 优势评估、置信度评分、凯利公式仓位管理

  • 套利 — Kalshi 和 Polymarket 之间的跨平台价差检测

  • 筛选 — 按交易量、波动和机会对市场进行批量评分

  • 表现 — 交易记录和校准指标

  • Webhooks — 价格变动和巨鲸交易的实时提醒

  • 快速入门 — 可用的 Python、curl 和 MCP 配置代码片段,5 分钟内即可上手

快速示例

"What are the top prediction markets right now?"
"Analyze the Fed rate decision market on Kalshi"
"Find arbitrage opportunities above 3% spread"
"Screen the top 50 Kalshi markets and analyze anything actionable"
"Show me a quickstart for Python"

教程

定价

层级

每次调用

包含内容

免费

$0.00

校准、健康检查

列表

$0.01

市场数据、价格历史

洞察

$0.10

分析、筛选、结算

策略

$2.00

信号、投资组合规模、共识

深度

$5.00

套利、相关性、Webhooks

免费计划:每月 100 次列表调用 + 10 次洞察调用。升级到 Pro 以获取更高限额。

链接

Available Tools

27 tools
analyze_marketA

Start a deep research analysis pipeline for a prediction market bet.

Returns immediately with an analysis_id. Poll with check_analysis_status every 5 seconds until complete, then retrieve results with get_analysis.

Args: bet_text: Description of the bet or market question to analyze. platform: Source platform hint: "kalshi", "polymarket", or "".

Inputs: bet_text (required), platform. Returns: result

check_analysis_statusA

Check the current status of a running or completed analysis.

Args: analysis_id: Analysis identifier returned by analyze_market.

Inputs: analysis_id (required). Returns: result

check_resolutionsA

Check all open trades for market resolution and update P&L.

Inputs: no named parameters. Returns: result

create_webhookA

Register a webhook for real-time event notifications.

Args: url: HTTPS URL to receive POST notifications. events: Event types: "whale_alert", "price_shift", "analysis_complete". secret: Optional shared secret for HMAC signature verification.

Inputs: url (required), events (required), secret. Returns: result

delete_webhookB

Remove a registered webhook.

Args: webhook_id: Webhook identifier returned by create_webhook.

Inputs: webhook_id (required). Returns: result

get_analysisA

Retrieve the full structured analysis result for a completed analysis.

Includes probability estimate, edge assessment, scenarios, key factors, risks, and trading recommendation.

Args: analysis_id: Analysis identifier for a completed analysis.

Inputs: analysis_id (required). Returns: result

get_arbitrageA

Get cross-platform arbitrage opportunities between Kalshi and Polymarket (cached).

Args: min_spread: Minimum spread threshold (0.0-1.0). Default 0.02 (2%).

Inputs: min_spread. Returns: result

get_arbitrage_liveA

Run a fresh cross-platform arbitrage scan (may take 10-30 seconds).

Args: min_spread: Minimum spread threshold (0.0-1.0). Default 0.02 (2%).

Inputs: min_spread. Returns: result

get_calibrationA

Get signal accuracy and calibration metrics — Brier score, hit rates, total signals.

Args: category: Filter by category (e.g. "crypto", "politics") or "" for all. period: Time period: "7d", "30d", "90d", or "all". mode: Trading mode: "shadow" or "live".

Inputs: category, period, mode. Returns: result

get_consensusB

Get consensus probability from aggregated agent trades.

Args: market_id: Platform-specific market identifier. platform: Platform: "kalshi" or "polymarket". period: Lookback period: "48h", "7d", or "30d".

Inputs: market_id (required), platform, period. Returns: result

get_correlationA

Compute cross-market correlation graph for portfolio diversification analysis.

Args: market_ids: List of market IDs to correlate (minimum 2). platform: Platform: "kalshi" or "polymarket". period: Lookback period: "48h", "7d", or "30d".

Inputs: market_ids (required), platform, period. Returns: result

get_execution_guidanceA

Get execution guidance for a market — spread analysis, slippage estimate, order recommendation.

Args: platform: Platform: "kalshi" or "polymarket". market_id: Platform-specific market identifier.

Inputs: platform (required), market_id (required). Returns: result

get_marketA

Get detailed information about a specific prediction market.

Args: market_id: Platform-specific market identifier (e.g. Kalshi ticker or Polymarket slug). source: Platform hint: "kalshi", "polymarket", or "" to search both.

Inputs: market_id (required), source. Returns: result

get_market_historyB

Get price history for a prediction market over a configurable period.

Args: platform: Platform: "kalshi" or "polymarket". market_id: Platform-specific market identifier. period: History window: "48h", "7d", or "30d". max_points: Maximum data points to return.

Inputs: platform (required), market_id (required), period, max_points. Returns: result

get_performanceB

Get aggregate trading performance statistics.

Args: mode: Portfolio mode: "shadow" for paper trades, "live" for real trades.

Inputs: mode. Returns: result

get_portfolioB

Get current portfolio positions and performance summary.

Args: mode: Portfolio mode: "shadow" for paper trades, "live" for real trades.

Inputs: mode. Returns: result

get_portfolio_strategyA

Get a portfolio-aware strategy signal with position context and correlation analysis.

Args: market_query: Description of the bet or market question to analyze. portfolio: Optional list of current positions (dicts with ticker, side, size_usd). bankroll_usd: Total bankroll in USD for position sizing. max_position_pct: Maximum fraction of bankroll per position.

Inputs: market_query (required), portfolio, bankroll_usd, max_position_pct. Returns: result

get_resolutionA

Get resolution intelligence for a market — time urgency, mechanism, theta estimate.

Args: platform: Platform: "kalshi" or "polymarket". market_id: Platform-specific market identifier.

Inputs: platform (required), market_id (required). Returns: result

get_strategyA

Run a full analysis and return a strategy signal with causal decomposition.

This is a blocking call that takes 30-90 seconds. For async control, use analyze_market + check_analysis_status + get_analysis instead.

Args: market_query: Description of the bet or market question to analyze. risk_limit: Reserved for position sizing constraints.

Inputs: market_query (required), risk_limit. Returns: result

list_analysesB

List recent analyses with summary information.

Args: limit: Maximum number of analyses to return.

Inputs: limit. Returns: result

list_marketsB

List current prediction markets from Kalshi and Polymarket.

Args: source: Filter by platform: "kalshi", "polymarket", or "" for all. limit: Maximum number of markets to return (1-100).

Inputs: source, limit. Returns: result

list_webhooksB

List registered webhooks.

Inputs: no named parameters. Returns: result

place_shadow_tradeA

Place a paper (shadow) trade on a prediction market for tracking purposes.

Args: ticker: Market ticker symbol (e.g. "KXBTC-100K"). side: Trade direction: "yes" or "no". size_usd: Trade size in USD.

Inputs: ticker (required), side (required), size_usd (required). Returns: result

report_tradeA

Report a trade for consensus probability aggregation.

Args: market_id: Platform-specific market identifier. platform: Platform: "kalshi" or "polymarket". side: Trade direction: "yes" or "no". size_usd: Trade size in USD. price: Execution price (0.0-1.0).

Inputs: market_id (required), platform (required), side (required), size_usd (required), +1 more. Returns: result

run_scraperA

Fetch fresh market data from a platform scraper.

Args: source: Which scraper to run: "kalshi", "polymarket", or "arbitrage".

Inputs: source (required). Returns: result

screen_marketsA

Batch screen markets by score, volume, or specific IDs.

Returns scored markets with an action recommendation: "analyze", "watch", or "skip".

Args: market_ids: Optional list of specific market IDs to screen. platform: Filter by platform: "kalshi", "polymarket", or "" for all. min_volume_24h: Minimum 24h volume filter. min_score: Minimum composite score filter. limit: Maximum number of results to return.

Inputs: market_ids, platform, min_volume_24h, min_score, +1 more. Returns: result

search_marketsA

Search prediction markets by keyword in market title.

Args: query: Search query string to match against market titles. limit: Maximum number of results to return.

Inputs: query (required), limit. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 27 tools

    Disambiguation3/5

    Most tools have distinct purposes, but there is notable overlap between analyze_market/get_strategy and get_arbitrage/get_arbitrage_live, which could confuse agents. Descriptions help clarify differences, but the boundaries are not always sharp.

    Naming Consistency5/5

    Tool names follow a highly consistent verb_noun pattern throughout, such as analyze_market, check_analysis_status, get_analysis, and list_markets. There are no deviations in naming conventions, making the set predictable and readable.

    Tool Count2/5

    With 27 tools, the count feels excessive for a prediction market analysis server, leading to potential complexity and overlap. A more focused set of 10-15 tools could better serve the domain without overwhelming agents.

    Completeness5/5

    The tool surface comprehensively covers the prediction market domain, including analysis, trading, portfolio management, data retrieval, and webhooks. There are no obvious gaps, supporting full CRUD/lifecycle operations and agent workflows effectively.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Provides AI-powered tools for searching Polymarket prediction markets and calculating financial metrics like expected value and Kelly bet sizing. It enables users to perform arbitrage scanning, news-based sentiment analysis, and market research through natural language interfaces.
      -
    • A
      license
      A
      quality
      D
      maintenance
      Prediction market probability oracle for AI agents. 26 tools across 500+ live markets from Kalshi and Polymarket. Cross-source arbitrage detection, structured TPF signals, Kelly Criterion sizing, agent performance tracking, and webhook alerts.
      9
      83 npm
      1
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      24/7 autonomous monitoring and edge detection for prediction markets (Kalshi & Polymarket). Features causal tree analysis, orderbook depth tracking, cross-venue comparison, and real-time alerts.
      16
      196 npm
      12
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Provides AI assistants with real-time prediction market consensus data, including probabilities, opportunities, signals, and settlements.
      5
      20 PyPI
      MIT