# BenAwf (remote · api.benawf.com)

BenAwf remote MCP for Strategy Lab. Streamable HTTP. Paper GA; live venue beta.

- Trust score: 80/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-02

## Components

- remote · `api.benawf.com`: 80/100 (this document), [markdown](https://verifymcp.io/servers/com-benawf-mcp/api.md), [page](https://verifymcp.io/servers/com-benawf-mcp/api)

## Channel facts

- Endpoint: `https://api.benawf.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-02.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 85/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2423 tokens (~115/item across 21 items; 16 tools + 5 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 85% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_entry_gate" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the BenAwf MCP server?

BenAwf is a hosted endpoint at https://api.benawf.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

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

### VS Code

```json
{
  "servers": {
    "com-benawf-mcp": {
      "type": "http",
      "url": "https://api.benawf.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-benawf-mcp]
url = "https://api.benawf.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-benawf-mcp": {
      "type": "remote",
      "url": "https://api.benawf.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-benawf-mcp --url 'https://api.benawf.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-benawf-mcp:
    url: "https://api.benawf.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-benawf-mcp": {
      "Transport": "http",
      "Url": "https://api.benawf.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-benawf-mcp -t streamable-http -u 'https://api.benawf.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-benawf-mcp": {
      "type": "http",
      "url": "https://api.benawf.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-02 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-30 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-28 (score 78, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 77, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-09-26 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-25 (score 76, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-23 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-22 (score 75, 0)

- [functional improvement] Stability: unverified → 0.03

## MCP tools (16)

### `list_iterations` (~67 tokens)

Open Lab @R# rows as the same dump as Live rules (parent, headline @B#, Long/Position/Exit).

Input parameters:

- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.

### `get_lineage` (~78 tokens)

Champion @R#, per-iteration verdicts, levers tried/untried/failed on champion, converged flag, and user canvas view vs recommended working @R#.

Input parameters:

- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.

### `select_iteration` (~75 tokens)

Load an @R# onto the live canvas so mutate tools edit that iteration.

Input parameters:

- `ref` (string, required): @R# to load onto the canvas (usually champion).
- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.

### `add_entry_gate` (~115 tokens)

Add 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.

Input parameters:

- `condition` (required): Translator-shaped entry gate condition.
- `side` (string, required): entry.long or entry.short.
- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.

### `patch_entry_gate` (~118 tokens)

Replace 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.

Input parameters:

- `condition` (required): Translator-shaped replacement condition.
- `id` (string, required): Gate id from get_experiment.rules.entry.
- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.

### `delete_entry_gate` (~88 tokens)

Remove one entry gate by id (from get_experiment). Args: id only. Refuses when it would leave both long and short with zero gates.

Input parameters:

- `id` (string, required): Gate id from get_experiment.rules.entry.
- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.

### `patch_position` (~158 tokens)

Full 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.

Input parameters:

- `position` (object, required): Full replace of rules.position (not a merge). Every key required. usdAmount XOR balancePercent (unused = 0). orderType = market|limit. limitPrice + expiresInMinutes = number | null (null unless limit…
- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.

### `patch_exit` (~255 tokens)

Full 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.

Input parameters:

- `exit` (object, required): Full replace of rules.exit (not a merge). Every key required — null disables: stopLossPercentage + takeProfitPercentage = 0–100 number OR {source,op,value,fallbackPercentage,minPercentage,maxPercenta…
- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.

### `patch_cooldown` (~107 tokens)

Set 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.

Input parameters:

- `cooldownMinutes` (required): Root cooldownMinutes, or null to clear.
- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.

### `list_strategies` (~75 tokens)

Ids, @R# refs, and backtest headlines for strategies not currently open.

Input parameters:

- `limit` (integer)
- `offset` (integer)
- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.

### `list_backtests` (~92 tokens)

Open Lab @B# rows with window, assets, trade count, PnL, win rate, drawdown, and tape_stripped.

Input parameters:

- `iteration_ref` (string): Optional @R#. Omit to retrieve backtests across all iterations.
- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.

### `get_backtest` (~261 tokens)

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 comment). After any mutate pass that result's dsl_ref. If you changed rules behind the same R#/draft, or suspect a stale cached @B#, pass force:true to force a fresh sim — never extrapolate from a cached B# of a different rules state.

Input parameters:

- `config` (object): Window + capital. Omit to reuse the previous run. Do not send empty strings or zeros.
- `force` (boolean): Skip the cache and force a fresh sim for this @R# + window. Use after any rule change on the same R#/draft, or whenever a cached B# is suspect.
- `ref` (string, required): @R# to sim. After mutate use that result's dsl_ref, not the Live-rules header.
- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.

### `list_trades` (~99 tokens)

One page of fills (20 per page): trade_id, side, prices, PnL.

Input parameters:

- `page` (integer, required)
- `ref` (string, required): Backtest @B# ref (e.g. B3 or @B3).
- `sort` (string, required)
- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.

### `get_experiment` (~102 tokens)

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.

Input parameters:

- `ref` (string, required): DSL iteration ref @R# (e.g. R2 or @R2).
- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.

### `diff_dsl` (~112 tokens)

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.

Input parameters:

- `ref_a` (string, required): First @R# to compare (older / baseline).
- `ref_b` (string, required): Second @R# to compare (newer).
- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.

### `get_market_context_by_date` (~110 tokens)

OHLCV and cited indicators around that date (engine lookback each side).

Input parameters:

- `date` (string, required)
- `strategy_id` (string): Strategy id. Prefer always: routes to that Lab tab, and NO_ACTIVE_LAB errors include a direct Lab URL to open.
- `symbol` (string, required)
- `time_frame` (number, required): OHLCV timeframe in minutes: 1, 5, 15, 30, 60, 240, 1440.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-benawf-mcp/api#diagnostics

## Score history

- 2026-10-02: 80
- 2026-10-01: 79
- 2026-09-30: 79
- 2026-09-29: 78
- 2026-09-28: 78
- 2026-09-27: 77
- 2026-09-26: 77
- 2026-09-25: 76
- 2026-09-24: 76
- 2026-09-23: 76
- 2026-09-22: 75
- 2026-09-21: 75

## Common questions

### What is the BenAwf MCP server?

BenAwf is an MCP server listed in the public MCP registry as com.benawf/mcp. BenAwf remote MCP for Strategy Lab. Streamable HTTP. Paper GA; live venue beta. This page covers its hosted endpoint (https://api.benawf.com/mcp).

### Is the BenAwf MCP server safe to use?

BenAwf scores 80 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the BenAwf MCP server expose?

BenAwf exposes 16 tools: list_iterations, get_lineage, select_iteration, add_entry_gate, patch_entry_gate, and 11 more. Their descriptions and schemas cost roughly 1,912 tokens of context every time the server is loaded.

### Does the BenAwf MCP server require authentication?

Yes. BenAwf asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the BenAwf MCP server still maintained?

BenAwf is still listed as active in the MCP registry. We last reached this channel on 2 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.benawf.com/mcp
- Website: https://benawf.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-benawf-mcp/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-benawf-mcp/api.json
- HTML version of this page: https://verifymcp.io/servers/com-benawf-mcp/api