coach_reply
Wingman dating/social coach: suggest the next reply(ies) given the live conversation. Free local model or BYOK. Returns {replies[], read, confidence}.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/coach-reply.md
What coach_reply does on Gateway
AI agents call coach_reply to retrieve information from Gateway without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
goal | string | — | e.g. 'get the date', optional |
count | integer | — | how many replies (1-5, default 3) |
model | string | — | provider model id (BYOK) |
handle | string | — | your handle (BYOK via vault) |
secret | string | — | your agent secret (BYOK via vault) |
api_key | string | — | inline provider key (BYOK) |
key_ref | string | — | vault entry name holding your LLM key (BYOK) |
provider | string | — | provider name (BYOK) |
conversation | array | Yes | turns as [{from, text}, ...] (or a transcript string) |
target_profile | string | — | the other person, optional |
Parameters from the server's own tool schema.
Why coach_reply is rated Low
This tool analyzes existing conversation data to generate suggestions for the user. It performs no writes, deletes, code execution, or financial transactions. The 'read' field in the return value confirms it is a read-only operation that retrieves and processes conversation context to produce recommendations.
From the tool's definition Tool description states it returns suggested replies based on input conversation data. The verb 'suggest' and 'given the live conversation' indicate data retrieval and analysis only.
Risk signalsHandles credentials or secrets (secret) · High parameter count (10 properties)
Attacks that exploit this kind of access
The rule that runs coach_reply 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_reply, this is the rule to start with:
coach_reply is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Gateway, apply this rule, and every coach_reply call is checked against it from then on.
Questions about coach_reply
Wingman dating/social coach: suggest the next reply(ies) given the live conversation. Free local model or BYOK. Returns {replies[], read, confidence}. It is categorised as a Read tool in the Gateway MCP Server, which means it retrieves data without modifying state.
coach_reply accepts 10 parameters: goal, count, model, handle, secret, api_key, key_ref, provider, conversation, target_profile. Required: conversation. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for coach_reply: 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.
coach_reply is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the coach_reply 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.
Set action: deny in the PolicyLayer policy for coach_reply. 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.
coach_reply 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.
More on Gateway, and thousands of servers like it.
This server
Across the catalogue