Documentation

Neural API Reference

Comprehensive documentation for the rlx-search engine telemetry and the MCP orchestration server.

Engine StatusOperational

Model Context Protocol

The MCP Server acts as a semantic gateway, exposing the full ai_patterns analysis surface to remote AI agents and internal swarm orchestration.

Transport Protocols

Local Stdio

Best for local development and direct integration with VS Code or Claude Desktop.

Remote HTTP

Production-grade endpoint for distributed agentic swarms via Nginx reverse-proxy.

POST /api/mcpActive

GET /api/mcp/referenceJSON REF

Tool Registry

Core Analysis

pattern_search

Execute deep recursive pattern scans across target assets.

get_pattern_metrics

Retrieve probability distributions and ensemble forecasts.

get_grid_stats

Analyze grid density and historical success rates.

backtest_strategy

Run high-fidelity strategy simulations against telemetry.

Market State

get_live_signals

Real-time pattern breakthrough and breakout signals.

get_dataset_status

Check synchronization health of pattern universe.

detect_market_regime

Identify current volatility and trend states.

Polymarket TTC Workflow

Advanced Probability Engine

Integrate Time-To-Close aware probabilities directly into trading agents. The MCP layer provides background watchers that maintain hot caches of pattern metrics specifically filtered for active prediction markets.

ensemble.closeAboveStrikeProb

ensemble.touchStrikeProb

ensemble.signal

Quick Start (Claude / Desktop)

mcp-config.json

Integration Config

{
  "mcpServers": {
    "ai_patterns_neural_link": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-server/dist/index.js"],
      "env": {
        "RLX_SEARCH_BASE_URL": "$BASE_URL",
        "SUPABASE_URL": "YOUR_URL"
      }
    }
  }
}