# send_feedback

Send feedback, bug report, or feature request to the Grabbit team. Use this when you encounter parsing failures, missing features, broken URLs, or have improvement suggestions. The team reads these to improve the product. Be specific about what went wrong and where.

Agent View of the PolicyLayer registry record for `send_feedback`. HTML page: https://policylayer.com/tools/com-grabbitapp-grabblist/send-feedback

## Facts

- Tool: `send_feedback`
- Server: Grabblist (`https://mcp.grabbitapp.com/api/mcp`) — https://policylayer.com/tools/com-grabbitapp-grabblist.md
- Homepage: https://github.com/https://mcp.grabbitapp.com/api/mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 5 (2 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `url` | string | no | The URL where the issue occurred |
| `tool` | string | no | The tool you were using when the issue occurred (e.g. add_item, search_saved) |
| `type` | string | yes | Type: bug (something broken), parsing_failure (price/title/image not extracted), feature_request (wishlist), feedback (general feedback) |
| `error` | string | no | Error message you received, if any |
| `message` | string | yes | What happened or what you propose. Be specific — the team reads this. |

Parameters from the server's own tool schema.

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "send_feedback",
    "arguments": {
      "type": "<type>",
      "message": "<message>"
    }
  }
}
```

## Why send_feedback is rated Medium

An AI agent can call send_feedback faster than any human can review: one bad instruction and it creates or modifies resources in Grabblist by the hundred, each call as confident as the last.

Risk signals: Accepts URL/endpoint input (url)

## Use case

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

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Grabblist:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_feedback": {
      "limits": [
        {
          "counter": "send_feedback_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Grabblist (22)

- `delete_collection` — Destructive — https://policylayer.com/tools/com-grabbitapp-grabblist/delete-collection.md
- `delete_item` — Destructive — https://policylayer.com/tools/com-grabbitapp-grabblist/delete-item.md
- `remove_from_collection` — Destructive — https://policylayer.com/tools/com-grabbitapp-grabblist/remove-from-collection.md
- `unlink_items` — Destructive — https://policylayer.com/tools/com-grabbitapp-grabblist/unlink-items.md
- `ask_agent` — Read — https://policylayer.com/tools/com-grabbitapp-grabblist/ask-agent.md
- `get_collection_activity` — Read — https://policylayer.com/tools/com-grabbitapp-grabblist/get-collection-activity.md
- `get_item` — Read — https://policylayer.com/tools/com-grabbitapp-grabblist/get-item.md
- `get_item_graph` — Read — https://policylayer.com/tools/com-grabbitapp-grabblist/get-item-graph.md
- `get_item_history` — Read — https://policylayer.com/tools/com-grabbitapp-grabblist/get-item-history.md
- `get_wishlist` — Read — https://policylayer.com/tools/com-grabbitapp-grabblist/get-wishlist.md
- `list_collections` — Read — https://policylayer.com/tools/com-grabbitapp-grabblist/list-collections.md
- `search_saved` — Read — https://policylayer.com/tools/com-grabbitapp-grabblist/search-saved.md
- `add_item` — Write — https://policylayer.com/tools/com-grabbitapp-grabblist/add-item.md
- `add_to_collection` — Write — https://policylayer.com/tools/com-grabbitapp-grabblist/add-to-collection.md
- `create_collection` — Write — https://policylayer.com/tools/com-grabbitapp-grabblist/create-collection.md
- `link_items` — Write — https://policylayer.com/tools/com-grabbitapp-grabblist/link-items.md
- `ping` — Write — https://policylayer.com/tools/com-grabbitapp-grabblist/ping.md
- `restore_item` — Write — https://policylayer.com/tools/com-grabbitapp-grabblist/restore-item.md
- `set_pinned_items` — Write — https://policylayer.com/tools/com-grabbitapp-grabblist/set-pinned-items.md
- `update_collection` — Write — https://policylayer.com/tools/com-grabbitapp-grabblist/update-collection.md
- `update_item` — Write — https://policylayer.com/tools/com-grabbitapp-grabblist/update-item.md
- `update_price` — Write — https://policylayer.com/tools/com-grabbitapp-grabblist/update-price.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=com-grabbitapp-grabblist · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-grabbitapp-grabblist