Analytics
benawf.com
MCP server for managing trading strategy iterations, inspecting lineage and champion verdicts, and editing entry gates on a live canvas.
ENDPOINT 1
https://api.benawf.com/mcp
MCP server metadata
- Name
- benawf
- Version
- 1.0.0
BenAwf MCP: you are the DSL translator. BenAwf does not call an LLM for your tools. **Requirement:** Strategy Lab must be open in the browser on the target strategy. If you get 409 NO_ACTIVE_LAB, tell the user to open the `lab_url` from the error (or the URL in the message), then retry. Always pass `strategy_id` when known so the error includes a direct Lab link. Mutate tools take translator-shaped JSON (condition / position / exit / cooldownMinutes) — not prose text. Browser applies only. get_backtest returns numbers only (you analyze). **Cache semantics:** get_backtest caches by (@R#, window) — same @R# + same window already simmed returns that cached @B# with identical stats (comment = "Cached @B#"). After any mutate pass the result's dsl_ref, and pass `force: true` whenever rules changed on the same R#/draft or a cached @B# is suspect (comment = "Fresh sim @B#"). The host also remaps a stale prior R# to the live dirty canvas — never trust a cached @B# for a rules state you changed. Discover DSL via resources: benawf://strategy-reference, benawf://rules-entry-mode, benawf://mcp-agent-workflow, benawf://product. Users who are not signed in: use prompt get_started or resource benawf://onboarding — they explain how to create an account and connect an API key. No load_skill / report_user_goal / ask_user / load_tools. Optional strategy_id on every tool routes to the matching Lab tab.
Known tools 16
list_iterationsOpen Lab @R# rows as the same dump as Live rules (parent, headline @B#, Long/Position/Exit).
Inferred read-onlyget_lineageChampion @R#, per-iteration verdicts, levers tried/untried/failed on champion, converged flag, and user canvas view vs recommended working @R#.
Inferred read-onlyselect_iterationLoad an @R# onto the live canvas so mutate tools edit that iteration.
Potential side effectslist_strategiesIds, @R# refs, and backtest headlines for strategies not currently open.
Inferred read-onlylist_backtestsOpen Lab @B# rows with window, assets, trade count, PnL, win rate, drawdown, and tape_stripped.
Potential side effectsget_backtestCache-or-run one sim for an @R# + window, then return Score, trade count, PnL, drawdown, and bounded stats for one run.
Potential side effectsget_experimentProse summary plus rules JSON (entry gates with ids, position, exit, cooldownMinutes) and that iteration's @B# refs.
Inferred read-onlydiff_dslStructured rules diff between two @R# iterations (entry gates per side, position, exit, cooldown).
Inferred read-onlyget_market_context_by_dateOHLCV and cited indicators around that date (engine lookback each side).
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.benawf]
url = "https://api.benawf.com/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"benawf": {
"type": "http",
"url": "https://api.benawf.com/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: benawf
Remote MCP URL: https://api.benawf.com/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"benawf": {
"url": "https://api.benawf.com/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"benawf": {
"type": "http",
"url": "https://api.benawf.com/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "benawf",
"transport": "streamable-http",
"url": "https://api.benawf.com/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for benawf.com was fetched 2026-09-22T23:26:34.821Z.
benawf.com is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.