BenAwf

Connect it to your AI

Claude Code

claude mcp add --transport http benawf https://api.benawf.com/mcp

Claude, ChatGPT, Cursor and other apps

Add it as a custom connector with this URL (Streamable HTTP):

https://api.benawf.com/mcp

Cursor, VS Code and other apps (mcp.json)

{
  "mcpServers": {
    "benawf": {
      "url": "https://api.benawf.com/mcp"
    }
  }
}

Tools it offers

16 tools, as the server itself reported during our check on Oct 31, 2026.

• list_iterationsOpen Lab @R# rows as the same dump as Live rules (parent, headline @B#, Long/Position/Exit).
• get_lineageChampion @R#, per-iteration verdicts, levers tried/untried/failed on champion, converged flag, and user canvas view vs recommended working @R#.
• select_iterationLoad an @R# onto the live canvas so mutate tools edit that iteration.
• add_entry_gateAdd one AND entry gate. Args: side + condition JSON. You are the DSL translator. Invent the section JSON (condition/position/exit/cooldown). Browser applies only — BenAwf does not call an LLM. No prose text.
• patch_entry_gateReplace one entry gate by id. Args: id + condition JSON. You are the DSL translator. Invent the section JSON (condition/position/exit/cooldown). Browser applies only — BenAwf does not call an LLM. No prose text.
• delete_entry_gateRemove one entry gate by id (from get_experiment). Args: id only. Refuses when it would leave both long and short with zero gates.
• patch_positionFull replace of rules.position. Args: position JSON. You are the DSL translator. Invent the section JSON (condition/position/exit/cooldown). Browser applies only — BenAwf does not call an LLM. No prose text.
• patch_exitFull replace of rules.exit. Args: exit JSON. You are the DSL translator. Invent the section JSON (condition/position/exit/cooldown). Browser applies only — BenAwf does not call an LLM. No prose text.
• patch_cooldownSet root cooldownMinutes. Args: cooldownMinutes number|null. You are the DSL translator. Invent the section JSON (condition/position/exit/cooldown). Browser applies only — BenAwf does not call an LLM. No prose text.
• list_strategiesIds, @R# refs, and backtest headlines for strategies not currently open.
• list_backtestsOpen Lab @B# rows with window, assets, trade count, PnL, win rate, drawdown, and tape_stripped.
• get_backtestCache-or-run one sim for an @R# + window, then return Score, trade count, PnL, drawdown, and bounded stats for one run. Numbers only — no BenAwf assessment LLM; you analyze. Same @R# + window → cached @B# (identical stat
• list_tradesOne page of fills (20 per page): trade_id, side, prices, PnL.
• get_experimentProse summary plus rules JSON (entry gates with ids, position, exit, cooldownMinutes) and that iteration's @B# refs. Read before inventing translator-shaped mutate args.
• diff_dslStructured rules diff between two @R# iterations (entry gates per side, position, exit, cooldown). Use before adopting an older iteration's levers onto a newer one.
• get_market_context_by_dateOHLCV and cited indicators around that date (engine lookback each side).

Questions