# generate_ai_project

Згенерувати повний проєкт з формами та звітами на основі текстового опису

Agent View of the PolicyLayer registry record for `generate_ai_project`. HTML page: https://policylayer.com/tools/com-quintadb-mcp/generate-ai-project

## Facts

- Tool: `generate_ai_project`
- Server: QuintaDB (`https://quintadb.com/mcp`) — https://policylayer.com/tools/com-quintadb-mcp.md
- Homepage: https://github.com/https://quintadb.com/mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 2 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `locale` | string | no | uk, en, ru |
| `description` | string | yes | Опис проєкту. Наприклад: 'CRM для клієнтів з угодами та аналітикою продажів' |

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_ai_project",
    "arguments": {
      "description": "<description>"
    }
  }
}
```

## Why generate_ai_project is rated Medium

This tool creates new database schemas, forms, and reports at scale based on natural language input. While reversible (Write, not Destructive), the blast radius is high because: (1) it can generate substantial database infrastructure with minimal safeguards, (2) an AI agent given uncontrolled access could generate unintended projects consuming resources, (3) the no-code nature means a non-technical misuse could…

From the tool's own definition: "Tool name 'generate_ai_project' and description 'Zgeneruvaty povnyy proyekt z formamy ta zvitamy na osnovi tekstovogo opysu' (Ukrainian: 'Generate full project with forms and reports based on text description') indicates creation of new database…"

## Use case

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

## Recommended policy (PolicyLayer)

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

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

## Other tools on QuintaDB (115)

- `delete_few_records` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/delete-few-records.md
- `delete_field` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/delete-field.md
- `delete_form` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/delete-form.md
- `delete_portal_group` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/delete-portal-group.md
- `delete_portal_menu_item` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/delete-portal-menu-item.md
- `delete_portal_user` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/delete-portal-user.md
- `delete_project` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/delete-project.md
- `delete_record` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/delete-record.md
- `delete_records_by_filter` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/delete-records-by-filter.md
- `delete_reminder` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/delete-reminder.md
- `delete_saved_view` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/delete-saved-view.md
- `delete_schedule` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/delete-schedule.md
- `delete_team_group` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/delete-team-group.md
- `delete_template` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/delete-template.md
- `delete_webhook` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/delete-webhook.md
- `remove_user_from_portal_group` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/remove-user-from-portal-group.md
- `remove_user_from_team_group` — Destructive — https://policylayer.com/tools/com-quintadb-mcp/remove-user-from-team-group.md
- `run_action` — Execute — https://policylayer.com/tools/com-quintadb-mcp/run-action.md
- `check_ai_site_status` — Read — https://policylayer.com/tools/com-quintadb-mcp/check-ai-site-status.md
- `describe_project` — Read — https://policylayer.com/tools/com-quintadb-mcp/describe-project.md
- `export_records` — Read — https://policylayer.com/tools/com-quintadb-mcp/export-records.md
- `fetch_url` — Read — https://policylayer.com/tools/com-quintadb-mcp/fetch-url.md
- `get_column_total` — Read — https://policylayer.com/tools/com-quintadb-mcp/get-column-total.md
- `get_field_types` — Read — https://policylayer.com/tools/com-quintadb-mcp/get-field-types.md
- `get_form_fields` — Read — https://policylayer.com/tools/com-quintadb-mcp/get-form-fields.md
- `get_form_settings` — Read — https://policylayer.com/tools/com-quintadb-mcp/get-form-settings.md
- `get_metric` — Read — https://policylayer.com/tools/com-quintadb-mcp/get-metric.md
- `get_portal_page` — Read — https://policylayer.com/tools/com-quintadb-mcp/get-portal-page.md
- `get_project` — Read — https://policylayer.com/tools/com-quintadb-mcp/get-project.md
- `get_quickstart_guide` — Read — https://policylayer.com/tools/com-quintadb-mcp/get-quickstart-guide.md
- …and 85 more: https://policylayer.com/tools/com-quintadb-mcp.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-quintadb-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-quintadb-mcp