# generate_prototype

根据已有项目 slug 或 PRD 配置生成/更新 prototype.html（Tailwind 高保真原型，含 PRD 标注弹框）。

Agent View of the PolicyLayer registry record for `generate_prototype`. HTML page: https://policylayer.com/tools/deppon-deppon-prd-mcp/generate-prototype

## Facts

- Tool: `generate_prototype`
- Server: Deppon Prd (`@deppon/deppon-prd-mcp`) — https://policylayer.com/tools/deppon-deppon-prd-mcp.md
- Install: `npx -y @deppon/deppon-prd-mcp`
- Homepage: https://www.npmjs.com/package/@deppon/deppon-prd-mcp
- Risk category: Write (Medium risk)
- Registry record: grade C, identity unverified
- Server rate-limited: no
- Parameters: 2 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `slug` | string | yes | 项目 slug |
| `regenerateFromConfig` | boolean | no | true 时从 project.config.json 重新生成 |

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": "generate_prototype",
    "arguments": {
      "slug": "<slug>"
    }
  }
}
```

## Why generate_prototype is rated Medium

This tool creates or updates a prototype.html file, which is a reversible write operation. It does not delete data (not Destructive), does not execute arbitrary code or shell commands (not Execute), involves no financial transactions (not Financial), and produces tangible outputs (not Read-only).

From the tool's own definition: "Tool description states '生成/更新 prototype.html' (generate/update prototype.html), indicating it creates or modifies files."

## Use case

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

## Recommended policy (PolicyLayer)

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

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

## Other tools on Deppon Prd (5)

- `export_canvas_handoff` — Read — https://policylayer.com/tools/deppon-deppon-prd-mcp/export-canvas-handoff.md
- `get_prd_project` — Read — https://policylayer.com/tools/deppon-deppon-prd-mcp/get-prd-project.md
- `list_prd_projects` — Read — https://policylayer.com/tools/deppon-deppon-prd-mcp/list-prd-projects.md
- `generate_prd` — Write — https://policylayer.com/tools/deppon-deppon-prd-mcp/generate-prd.md
- `open_prd_studio` — Write — https://policylayer.com/tools/deppon-deppon-prd-mcp/open-prd-studio.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=deppon-deppon-prd-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/deppon-deppon-prd-mcp