coach_mission
Wingman dating/social coach: a small gamified practice drill to build a dating skill today. Free local model or BYOK. Returns {mission, why, success_metric}.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/coach-mission.md
What coach_mission does on Gateway
AI agents invoke coach_mission to trigger actions in Gateway. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
focus | string | — | skill to target, e.g. 'openers' |
level | string | — | beginner|intermediate|advanced |
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) |
Parameters from the server's own tool schema.
Why coach_mission is rated High
This tool triggers execution of a coaching simulation/drill rather than simply retrieving static data. While the operation itself is not destructive, financial, or obviously harmful, it executes a behavioral intervention with side effects (practice session state, user engagement tracking). The 'gamified' nature and reference to 'skill building' suggest interactive execution.
From the tool's definition Tool executes a 'gamified practice drill' with external behavioral outcomes. Description indicates it runs a coach mission that returns structured results (mission, why, success_metric), implying code execution and state changes in a coaching simulation or…
Risk signalsHandles credentials or secrets (secret)
Attacks that exploit this kind of access
The rule that runs coach_mission 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_mission, this is the rule to start with:
coach_mission stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. 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_mission call is checked against it from then on.
Questions about coach_mission
Wingman dating/social coach: a small gamified practice drill to build a dating skill today. Free local model or BYOK. Returns {mission, why, success_metric}. It is categorised as a Execute tool in the Gateway MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
coach_mission accepts 8 parameters: focus, level, model, handle, secret, api_key, key_ref, provider. 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_mission: 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_mission is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the coach_mission 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_mission. 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_mission 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.
Across the catalogue