alforge-labs/alpha-forge-mcp

> **The MCP server for AlphaForge** — the agent-native quant CLI: write strategies in JSON, optimize with Optuna TPE, validate with walk-forward, export to TradingView Pine v6. This server lets your AI agent drive the whole pipeline over MCP. → **Try AlphaForge free**
---
A Model Context Protocol (MCP) server that exposes the
**AlphaForge alpha-forge CLI** to AI coding agents — Claude Code, Cursor, Codex, and any
MCP-capable client — over **stdio**.
It is a thin **open-source wrapper**: it shells out to the (commercial, closed-source)
alpha-forge binary with --json and returns the parsed result. The MCP server itself
contains no core logic — alpha-forge plus a valid license are required for anything to
actually run.
Tools
| Tool | What it does | Underlying command |
|------|--------------|--------------------|
| list_strategies | List registered strategies | alpha-forge strategy list --json |
| get_strategy | Full JSON of one strategy | alpha-forge strategy show --json |
| list_results | List saved backtest results | alpha-forge backtest list [--strategy ] --json |
| get_result | Metrics of one result (heavy arrays folded into counts by default; summary=false for full) | alpha-forge backtest report --json |
| run_backtest | Run a backtest (summary=true by default omits heavy arrays) | alpha-forge backtest run --strategy [--start] [--end] [--summary] --json |
| run_optimize | Optimize parameters (Optuna) | alpha-forge optimize run --strategy [--metric] [--trials] [--save] --json |
| apply_optimization | Apply an optimization result file to a strategy | alpha-forge optimize apply --to-strategy --yes |
| run_walk_forward | Walk-forward (out-of-sample) optimization | alpha-forge optimize walk-forward --strategy [--windows] [--metric] --json |
| run_monte_carlo | Monte Carlo from a saved result | alpha-forge backtest monte-carlo [--simulations] --json |
| fetch_data | Fetch & cache historical OHLCV (prereq for run_backtest) | alpha-forge data fetch [--period] |
| save_strategy | Register a strategy from its JSON **body** | alpha-forge strategy save |
| generate_pinescript | Generate Pine Script v6 source | alpha-forge pine preview --strategy [--with-webhook] |
| forge_status | Report capabilities/prerequisites (doctor + version) | alpha-forge system doctor --json |
| list_journals | List strategies that have a journal | alpha-forge journal list --json |
| get_journal | Full journal (snapshots, runs, tags, notes) of one strategy | alpha-forge journal show --json |
| exploration_status | Strategy-exploration coverage map (explored vs. untried) | alpha-forge explore status [--goal] --json |
| get_indicator | Metadata for one technical indicator | alpha-forge analyze indicator show --json |
save_strategy takes the strategy-definition **JSON body** as a string (not a file path,
which is more agent-friendly); it is written to a temp file before strategy save.
fetch_data exposes only period because the CLI has no --start/--end. forge_status
is read-only and never fails when the binary is missing — it returns binary_found: false
so a client can triage prerequisites before doing anything else.
run_optimize saves the result by default (save=true) so its saved_path can be passed
to apply_optimization, which applies the optimized parameters and saves
_optimized (it runs non-interactively with --yes). get_indicator returns
indicator **metadata** only (description, parameters, output) — the CLI has no
compute-over-symbol command, so it does not calculate the indicator on price data.
journal/explore reads are exposed read-first; write-oriented and ml/pairs commands are not
exposed yet.
The metric argument of run_optimize / run_walk_forward is a constrained **enum**
(sharpe_ratio (default), sortino_ratio, calmar_ratio, total_return_pct, cagr_pct,