BenAwf is a remote MCP server that gives an AI agent 16 tools, among them add_entry_gate, delete_entry_gate, diff_dsl. It answers at https://api.benawf.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 23 September 2026; the last check, on 7 November 2026, succeeded.
BenAwf remote MCP for Strategy Lab. Streamable HTTP. Paper GA; live venue beta.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
add_entry_gate | Add one AND entry gate. Args: side + condition JSON. You are the DSL translator. Invent the section JSON (condition/position/exit/cooldown). Lab applies only — BenAwf does not call an LLM. No prose text. Inputs: side, condition, strategy_id |
delete_entry_gate | Remove one entry gate by id (from get_experiment). Args: id only. Refuses when it would leave both long and short with zero gates. Inputs: id, strategy_id |
diff_dsl | Structured 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. Inputs: ref_a, ref_b, strategy_id |
get_backtest | Cache-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 stats; follow the commen Inputs: ref, force, config, strategy_id |
get_experiment | Prose summary plus rules JSON (entry gates with ids, position, exit, cooldownMinutes) and that iteration's @B# refs. Read before inventing translator-shaped mutate args. Inputs: ref, strategy_id |
get_lineage | Champion @R#, per-iteration verdicts, levers tried/untried/failed on champion, converged flag, and user canvas view vs recommended working @R#. Inputs: strategy_id |
get_market_context_by_date | OHLCV and cited indicators around that date (engine lookback each side). Inputs: symbol, date, time_frame, strategy_id |
list_backtests | Open Lab @B# rows with window, assets, trade count, PnL, win rate, drawdown, and tape_stripped. Inputs: iteration_ref, strategy_id |
list_iterations | Open Lab @R# rows as the same dump as Live rules (parent, headline @B#, Long/Position/Exit). Inputs: strategy_id |
list_strategies | Ids, @R# refs, and backtest headlines for strategies not currently open. Inputs: limit, offset, strategy_id |
list_trades | One page of fills (20 per page): trade_id, side, prices, PnL. Inputs: ref, page, sort, strategy_id |
patch_cooldown | Set root cooldownMinutes. Args: cooldownMinutes number|null. You are the DSL translator. Invent the section JSON (condition/position/exit/cooldown). Lab applies only — BenAwf does not call an LLM. No prose text. Inputs: cooldownMinutes, strategy_id |
patch_entry_gate | Replace one entry gate by id. Args: id + condition JSON. You are the DSL translator. Invent the section JSON (condition/position/exit/cooldown). Lab applies only — BenAwf does not call an LLM. No prose text. Inputs: id, condition, strategy_id |
patch_exit | Full replace of rules.exit. Args: exit JSON. You are the DSL translator. Invent the section JSON (condition/position/exit/cooldown). Lab applies only — BenAwf does not call an LLM. No prose text. |
patch_position | Full replace of rules.position. Args: position JSON. You are the DSL translator. Invent the section JSON (condition/position/exit/cooldown). Lab applies only — BenAwf does not call an LLM. No prose text. Inputs: position, strategy_id |
select_iteration | Load an @R# onto the live canvas so mutate tools edit that iteration. Inputs: ref, strategy_id |
Every block below points at https://api.benawf.com/mcp. Pick your client and copy.
claude mcp add --transport http benawf https://api.benawf.com/mcp
{
"mcpServers": {
"benawf": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.benawf.com/mcp"]
}
}
}{
"mcpServers": {
"benawf": {
"url": "https://api.benawf.com/mcp"
}
}
}{
"servers": {
"benawf": {
"type": "http",
"url": "https://api.benawf.com/mcp"
}
}
}{
"context_servers": {
"benawf": {
"url": "https://api.benawf.com/mcp"
}
}
}{
"mcpServers": {
"benawf": {
"serverUrl": "https://api.benawf.com/mcp"
}
}
}{
"mcpServers": {
"benawf": {
"url": "https://api.benawf.com/mcp"
}
}
}name: BenAwf
version: 0.0.1
schema: v1
mcpServers:
- name: BenAwf
type: streamable-http
url: https://api.benawf.com/mcp{
"mcpServers": {
"benawf": {
"httpUrl": "https://api.benawf.com/mcp"
}
}
}{
"mcpServers": {
"benawf": {
"type": "http",
"url": "https://api.benawf.com/mcp"
}
}
}{
"mcpServers": {
"benawf": {
"url": "https://api.benawf.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.benawf.com%2Fmcp&type=streamable_http&id=benawf&name=BenAwf
It answered our last check on 7 November 2026 in 172 ms. Over 4 checks since 23 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by benawf.com and served from api.benawf.com, the vendor's own domain: https://api.benawf.com/mcp.
16, as returned by the server's own tools/list on 12 November 2026: add_entry_gate, delete_entry_gate, diff_dsl, get_backtest, get_experiment, get_lineage, get_market_context_by_date, list_backtests, and 8 more.
It answered our last check on 7 November 2026 in 172 ms. Over 4 checks since 23 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.benawf.com/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.benawf. Endpoint host: api.benawf.com. ARD identifier: urn:air:com.benawf:mcp:mcp.
First indexed 21 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.