Skip to main content

MCP server for Rekko AI prediction market intelligence

Project description

Rekko MCP

PyPI License: MIT Python 3.11+

Prediction market intelligence for AI coding assistants. Deep causal research, arbitrage detection, screening, and strategy signals for Kalshi, Polymarket, and Robinhood.

Install

# Zero-install via uvx
uvx rekko-mcp

# Or install from PyPI
pip install rekko-mcp

Claude Code

claude mcp add rekko -- uvx rekko-mcp

Or add to .mcp.json:

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

Cursor / Windsurf

Add to your MCP configuration with the same uvx rekko-mcp command and REKKO_API_KEY env var.

Setup

  1. Get an API key at rekko.ai (free tier available)
  2. Set your key: export REKKO_API_KEY=rk_free_...
  3. Start using — tools appear as mcp__rekko__* automatically

Example prompts

  • "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 my shadow portfolio performance"

What you get

25 MCP tools integrated natively into your AI assistant:

Category Tools
Market intelligence list_markets, get_market, search_markets, get_market_history, get_resolution, get_execution_guidance
Screening screen_markets, get_calibration
Deep research analyze_market, check_analysis_status, get_analysis, list_analyses
Strategy get_strategy, get_portfolio_strategy, get_consensus
Arbitrage get_arbitrage, get_arbitrage_live
Correlation get_correlation
Trading place_shadow_trade, report_trade, get_portfolio, get_performance, check_resolutions
Data run_scraper
Webhooks create_webhook, list_webhooks, delete_webhook

Pricing

Tier Price/call What you get
Free $0.00 Calibration metrics, health check
Listing $0.01 Browse and search markets, price history
Insight $0.10 Start analyses, screen markets, resolution intelligence
Strategy $2.00 Strategy signals, portfolio-aware sizing, consensus
Deep $5.00 Arbitrage scanning, correlation analysis, webhooks

Full pricing details at rekko.ai/docs/pricing.

Chaining with execution skills

Rekko provides the intelligence — chain with execution skills for trading:

  • PolyClaw — execute trades on Polymarket
  • Kalshi Trader — execute trades on Kalshi

Example flow: Rekko analysis → strategy signal → PolyClaw executes the trade.

Links

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

rekko_mcp-0.1.0.tar.gz (11.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

rekko_mcp-0.1.0-py3-none-any.whl (8.4 kB view details)

Uploaded Python 3

File details

Details for the file rekko_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: rekko_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 11.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for rekko_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 1a629d21445cf82e65c73fac90ee092b6c339c48fc2c1dd510986a40bbc59c9c
MD5 2ae40d48a7996d638e835b24f5cb7b89
BLAKE2b-256 6dbfe8bac3ed928a04445e66ac43dcd8c0bf0bf2dedd2eb34befcab1d371dfb6

See more details on using hashes here.

Provenance

The following attestation bundles were made for rekko_mcp-0.1.0.tar.gz:

Publisher: publish.yml on Rekko-AI/rekko-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file rekko_mcp-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: rekko_mcp-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 8.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for rekko_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 744d203ca85c4bc6b562029e829c2eff0edff5be9bbce0f382ba8fc80fa315b7
MD5 a99fde3520db21443b716980d92807c8
BLAKE2b-256 d244849350382c208a82802fd6150ae028174d68ae440dbea7ad0665de1bdb60

See more details on using hashes here.

Provenance

The following attestation bundles were made for rekko_mcp-0.1.0-py3-none-any.whl:

Publisher: publish.yml on Rekko-AI/rekko-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page