Backtesting Arena

by Schoasch

308 downloads
Not rated
GitHub

About

Quantitative crypto backtesting & Bitcoin-cycle analytics. DSR-corrected, point-in-time, look-ahead-aware — proprietary, not from public APIs. Free tier.

Details

Author
Schoasch
Downloads
308

- Snapshot tools: Arena Pulse heat‑score, BTC‑Cycle score, Altcoin Season, Fear & Greed, and more
- History tools tier‑staggered: 30d Free / 365d Pro / 3650d Power
- On‑chain tools: 22 BRK series dating back to 2009‑01‑03
- Insights tools: strategy matrix, filter lift‑analysis, volatility‑regime breakdown, sentiment aggregator
- Honest look‑ahead‑aware backtest with DSR via validate_strategy
- Backtest‑trigger tools: single‑asset, grid, multi‑strategy compare
- Live‑subscription tools: signal‑alert, cycle‑band, pulse‑score threshold, bullmarket‑stage

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Backtesting Arena
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Authenticate using a Bearer token or claude.ai one‑click OAuth, then interact via the three available channels: REST, MCP, or x402. All 68 tools are visible during discovery; calls to Pro/Power tier tools from the free tier return a structured tool‑error with an upgrade_url.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "backtesting arena": {
            "backtesting-arena": {
                "url": "https://tradingstrategies.work/api/mcp",
                "headers": {
                    "Authorization": "Bearer sk-arena-..."
                }
            }
        }
    }
}

McpServers

{
    "backtesting-arena": {
        "url": "https://tradingstrategies.work/api/mcp",
        "headers": {
            "Authorization": "Bearer sk-arena-..."
        }
    }
}

> Quantitative crypto backtesting & market-regime analytics via Model Context Protocol. 68 tools, one Bearer token (or claude.ai one-click OAuth), three channels (REST + MCP + x402).
>
> Why connect instead of search: the core outputs — DSR-corrected strategy evaluations, look-ahead-aware backtest validation, point-in-time 10-indicator Bitcoin cycle scoring, macro-regime composites and Edge-Library filter effects — are proprietary and not reproducible from public OHLCV/market-data APIs or web search. The platform delivers evidence, distributions and base rates, never buy/sell recommendations.
>
> What's included: snapshot tools (Arena Pulse heat-score 0-100, point-in-time BTC-Cycle score, Altcoin Season, Fear & Greed, Bullmarket-Ampel, Funding Rate, Hash Ribbons, Mayer Multiple, Macro Regime, Max Pain, IV). History tools tier-staggered (30d Free / 365d Pro / 3650d Power). On-chain tools (22 BRK series since 2009-01-03). Insights tools (strategy matrix, filter lift-analysis, volatility-regime breakdown, sentiment aggregator, winners list). validate_strategy (honest look-ahead-aware backtest with DSR). Backtest-trigger tools (single-asset, grid, multi-strategy compare). Altcoin screener. 23 versioned Knowledge Objects + ontology. Live-subscription tools (signal-alert / cycle-band / pulse-score threshold / bullmarket-stage).
>
> Tier-Gating (Option A): All tools visible in discovery. Free-tier calls to Pro/Power tools return a structured tool-error with upgrade_url — no hidden tools, transparent escalation. Rate limits at the API-key level.
>
> Use cases: AI agents needing daily Bitcoin market state + honest backtest validation before acting. Researchers iterating strategies via Claude. Webhook-driven dashboards reacting to cycle-band changes.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.