Rekko MCP

Instructions

Implementation Reference

• src/rekko_mcp/server.py:273-295 (handler)

  The 'get_portfolio_strategy' function is a tool handler that constructs a request body with portfolio and market parameters, then makes an asynchronous POST request to the '/v1/signals/portfolio' endpoint to retrieve a strategy signal.

  @mcp.tool()
  async def get_portfolio_strategy(
      market_query: str,
      portfolio: list[dict] | None = None,
      bankroll_usd: float = 10000.0,
      max_position_pct: float = 0.05,
  ) -> str:
      """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.
      """
      body: dict = {
          "market_query": market_query,
          "bankroll_usd": bankroll_usd,
          "max_position_pct": max_position_pct,
      }
      if portfolio:
          body["portfolio"] = portfolio
      return await _request("POST", "/v1/signals/portfolio", json=body)