# drop

Drop an item you hold.

Agent View of the PolicyLayer registry record for `drop`. HTML page: https://policylayer.com/tools/a2a-mcp-world/drop

## Facts

- Tool: `drop`
- Server: A2A-MCP-World (`akshaytp749/A2A-MCP-World`) — https://policylayer.com/tools/a2a-mcp-world.md
- Homepage: https://github.com/akshaytp749/A2A-MCP-World
- Risk category: Destructive (Critical risk)
- Registry record: grade D, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Hidden

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

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

## Why drop is rated Critical

Dropping an item removes it from the agent's possession without a clear undo mechanism. In a persistent multi-agent world, once dropped, the item can be picked up by other agents or lost, making the action effectively irreversible. This places it closer to Destructive than Write, though the severity is medium rather than high since items are virtual within a game-like environment.

From the tool's own definition: "'Drop an item you hold' — releasing/dropping an item from inventory could be irreversible if another agent picks it up or the item is lost in the world state."

## Use case

AI agents call drop to permanently remove resources in A2A-MCP-World, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

## Recommended policy (PolicyLayer)

Verdict: **Hidden**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches A2A-MCP-World:

```json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "drop"
  ]
}
```

## Other tools on A2A-MCP-World (13)

- `move_to` — Execute — https://policylayer.com/tools/a2a-mcp-world/move-to.md
- `emote` — Read — https://policylayer.com/tools/a2a-mcp-world/emote.md
- `look` — Read — https://policylayer.com/tools/a2a-mcp-world/look.md
- `recall` — Read — https://policylayer.com/tools/a2a-mcp-world/recall.md
- `recall_events` — Read — https://policylayer.com/tools/a2a-mcp-world/recall-events.md
- `who` — Read — https://policylayer.com/tools/a2a-mcp-world/who.md
- `give` — Write — https://policylayer.com/tools/a2a-mcp-world/give.md
- `pick_up` — Write — https://policylayer.com/tools/a2a-mcp-world/pick-up.md
- `remember` — Write — https://policylayer.com/tools/a2a-mcp-world/remember.md
- `say` — Write — https://policylayer.com/tools/a2a-mcp-world/say.md
- `trade_offer` — Write — https://policylayer.com/tools/a2a-mcp-world/trade-offer.md
- `trade_respond` — Write — https://policylayer.com/tools/a2a-mcp-world/trade-respond.md
- `whisper` — Write — https://policylayer.com/tools/a2a-mcp-world/whisper.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=a2a-mcp-world · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a2a-mcp-world