# order_pizza

Orders a pizza with optional toppings through user elicitation.

Agent View of the PolicyLayer registry record for `order_pizza`. HTML page: https://policylayer.com/tools/abdullah-1121-mcp-2/order-pizza

## Facts

- Tool: `order_pizza`
- Server: MCP Chat (`abdullah-1121/mcp-2`) — https://policylayer.com/tools/abdullah-1121-mcp-2.md
- Homepage: https://github.com/Abdullah-1121/MCP-2
- Risk category: Financial (Critical risk)
- Registry record: grade B, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Approval-gated

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

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

## Why order_pizza is rated Critical

Ordering a pizza constitutes a financial commitment: it places a real order that incurs a monetary charge. Even though it uses 'user elicitation' (implying some confirmation step), the tool's core action is initiating a purchase transaction. This falls squarely in the Financial category, which is the most severe applicable category.

From the tool's own definition: "'Orders a pizza' — committing to a real-world purchase/financial transaction for food delivery"

## Use case

AI agents use order_pizza to commit financial operations through MCP Chat, usually the final step of a payment, billing, or trading workflow. A call moves real money.

## Recommended policy (PolicyLayer)

Verdict: **Approval-gated**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches MCP Chat:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "order_pizza": {
      "deny_if": [
        {
          "conditions": [],
          "on_deny": "Requires human approval."
        }
      ]
    }
  }
}
```

## Other tools on MCP Chat (7)

- `process_item` — Other — https://policylayer.com/tools/abdullah-1121-mcp-2/process-item.md
- `analyze_project` — Read — https://policylayer.com/tools/abdullah-1121-mcp-2/analyze-project.md
- `download_file` — Read — https://policylayer.com/tools/abdullah-1121-mcp-2/download-file.md
- `process_data` — Read — https://policylayer.com/tools/abdullah-1121-mcp-2/process-data.md
- `read_doc_contents` — Read — https://policylayer.com/tools/abdullah-1121-mcp-2/read-doc-contents.md
- `create_story` — Write — https://policylayer.com/tools/abdullah-1121-mcp-2/create-story.md
- `edit_document` — Write — https://policylayer.com/tools/abdullah-1121-mcp-2/edit-document.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=abdullah-1121-mcp-2 · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/abdullah-1121-mcp-2