# get_recommendation

Get a personalized recommendation for what to do next.

Agent View of the PolicyLayer registry record for `get_recommendation`. HTML page: https://policylayer.com/tools/94aharris-coach-ai/get-recommendation

## Facts

- Tool: `get_recommendation`
- Server: Coach AI (`94aharris/coach-ai`) — https://policylayer.com/tools/94aharris-coach-ai.md
- Homepage: https://github.com/94aharris/coach-ai
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_recommendation",
    "arguments": {}
  }
}
```

## Why get_recommendation is rated Low

This tool queries the system's stored user patterns and preferences to return a suggestion. It does not create, modify, delete, execute code, or move money. It is purely informational—the user must still decide whether to act on the recommendation. The most severe risk is a recommendation being unhelpful or biased, which has minimal blast radius for an AI agent. No destructive or financial operations are possible.

From the tool's own definition: "Tool name 'get_recommendation' and description 'Get a personalized recommendation for what to do next' indicate a query/retrieval operation."

## Use case

AI agents call get_recommendation to retrieve information from Coach AI without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Coach AI:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_recommendation": {}
  }
}
```

## Other tools on Coach AI (27)

- `delete_todo` — Destructive — https://policylayer.com/tools/94aharris-coach-ai/delete-todo.md
- `parse_task_list` — Execute — https://policylayer.com/tools/94aharris-coach-ai/parse-task-list.md
- `start_my_day` — Execute — https://policylayer.com/tools/94aharris-coach-ai/start-my-day.md
- `start_my_week` — Execute — https://policylayer.com/tools/94aharris-coach-ai/start-my-week.md
- `generate_daily_summary` — Read — https://policylayer.com/tools/94aharris-coach-ai/generate-daily-summary.md
- `get_daily_note_path` — Read — https://policylayer.com/tools/94aharris-coach-ai/get-daily-note-path.md
- `get_user_context` — Read — https://policylayer.com/tools/94aharris-coach-ai/get-user-context.md
- `list_goals` — Read — https://policylayer.com/tools/94aharris-coach-ai/list-goals.md
- `list_todos` — Read — https://policylayer.com/tools/94aharris-coach-ai/list-todos.md
- `read_daily_note_full` — Read — https://policylayer.com/tools/94aharris-coach-ai/read-daily-note-full.md
- `read_daily_note_section` — Read — https://policylayer.com/tools/94aharris-coach-ai/read-daily-note-section.md
- `sync_from_daily_note` — Read — https://policylayer.com/tools/94aharris-coach-ai/sync-from-daily-note.md
- `add_daily_note_section` — Write — https://policylayer.com/tools/94aharris-coach-ai/add-daily-note-section.md
- `add_task_context` — Write — https://policylayer.com/tools/94aharris-coach-ai/add-task-context.md
- `add_todo` — Write — https://policylayer.com/tools/94aharris-coach-ai/add-todo.md
- `add_user_fact` — Write — https://policylayer.com/tools/94aharris-coach-ai/add-user-fact.md
- `batch_assign_timeframes` — Write — https://policylayer.com/tools/94aharris-coach-ai/batch-assign-timeframes.md
- `brain_dump_tasks` — Write — https://policylayer.com/tools/94aharris-coach-ai/brain-dump-tasks.md
- `break_down_task` — Write — https://policylayer.com/tools/94aharris-coach-ai/break-down-task.md
- `complete_todo` — Write — https://policylayer.com/tools/94aharris-coach-ai/complete-todo.md
- `create_daily_note` — Write — https://policylayer.com/tools/94aharris-coach-ai/create-daily-note.md
- `log_accomplishment` — Write — https://policylayer.com/tools/94aharris-coach-ai/log-accomplishment.md
- `set_goal` — Write — https://policylayer.com/tools/94aharris-coach-ai/set-goal.md
- `set_todo_timeframe` — Write — https://policylayer.com/tools/94aharris-coach-ai/set-todo-timeframe.md
- `set_week_theme` — Write — https://policylayer.com/tools/94aharris-coach-ai/set-week-theme.md
- `sync_daily_note` — Write — https://policylayer.com/tools/94aharris-coach-ai/sync-daily-note.md
- `write_daily_note_section` — Write — https://policylayer.com/tools/94aharris-coach-ai/write-daily-note-section.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=94aharris-coach-ai · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/94aharris-coach-ai