coach_opener

SERVERGateway SOURCEhttps://wingmanprotocol.com/mcp

Medium RISK CLASS

Category Write

Parameters 101 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/com-wingmanprotocol-agent-gateway/coach-opener.md

WHAT IT DOES

What coach_opener does on Gateway

AI agents use coach_opener to create or update resources in Gateway, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gateway environment.

Parameter	Type	Required	Description
`tone`	string	—	playful\|direct\|witty\|warm, optional
`count`	integer	—	how many openers (1-5, default 3)
`model`	string	—	provider model id (BYOK), optional
`handle`	string	—	your registered handle (only for BYOK via vault)
`secret`	string	—	your agent secret (only for BYOK via vault)
`api_key`	string	—	inline provider key (BYOK alternative to key_ref)
`key_ref`	string	—	name of a vault entry holding your LLM provider key (BYOK)
`provider`	string	—	openai\|anthropic\|groq\|together\|openrouter\|mistral\|xai\|google (BYOK)
`my_profile`	string	—	your own profile, optional
`target_profile`	string	Yes	who you want to message (bio/interests; string or JSON)

Parameters from the server's own tool schema.

RISK

Why coach_opener is rated Medium

This tool generates dating/social coaching messages tailored to user input. It creates new text content but does not modify, delete, execute code, move money, or trigger external side effects beyond message composition. The write is reversible (messages can be discarded or edited).

From the tool's definition Tool description states it will 'write cold-open message(s)' and 'Returns {openers[], why, confidence}' — the primary action is generating/composing text (write) that will be returned to the caller.

Risk signalsHandles credentials or secrets (secret) · High parameter count (10 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs coach_opener safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For coach_opener, this is the rule to start with:

coach_opener Rate-limited

coach_opener stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "coach_opener": {
      "limits": [
        {
          "counter": "coach_opener_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Gateway, apply this rule, and every coach_opener call is checked against it from then on.

FAQ

Questions about coach_opener

What does the coach_opener tool do? +

Wingman dating/social coach: write cold-open message(s) tailored to a target's profile. Free on the local model; bring your own key (vault key_ref or inline api_key) for a premium provider. Returns {openers[], why, confidence}. It is categorised as a Write tool in the Gateway MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does coach_opener accept? +

coach_opener accepts 10 parameters: tone, count, model, handle, secret, api_key, key_ref, provider, my_profile, target_profile. Required: target_profile. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on coach_opener? +

Register the Gateway MCP server in PolicyLayer and add a rule for coach_opener: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Gateway. Nothing to install.

What risk level is coach_opener? +

coach_opener is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit coach_opener? +

Yes. Add a rate_limit block to the coach_opener rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block coach_opener completely? +

Set action: deny in the PolicyLayer policy for coach_opener. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides coach_opener? +

coach_opener is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Gateway, and thousands of servers like it.

This server

All 271 Gateway tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →