Genera una Server Action siguiendo los patrones del proyecto: - "use server" al inicio - Validación con Zod 4 usando safeParse - Autenticación con auth() de NextAuth si se requiere - Tipos de retorno explícitos - Revalidación de cache si aplica Args: - entity: nombre de la entidad (ej: "user", "p...
Part of the Project server.
Free to start. No card required.
AI agents use generate_action to create or modify resources in Project. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call generate_action repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Project.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"generate_action": {
"limits": [
{
"counter": "generate_action_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Project policy for all 10 tools.
These attack patterns abuse exactly the kind of access generate_action gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Genera una Server Action siguiendo los patrones del proyecto: - "use server" al inicio - Validación con Zod 4 usando safeParse - Autenticación con auth() de NextAuth si se requiere - Tipos de retorno explícitos - Revalidación de cache si aplica Args: - entity: nombre de la entidad (ej: "user", "post", "invoice") - operation: tipo de operación CRUD - with_auth: si requiere sesión autenticada (default: true) - prisma_schema: en qué schema de Prisma está la entidad Returns: código TypeScript listo para copiar a server/actions/[entity].ts. It is categorised as a Write tool in the Project MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Project MCP server in PolicyLayer and add a rule for generate_action: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Project. Nothing to install.
generate_action is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the generate_action rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for generate_action. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
generate_action is provided by the Project MCP server (project-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 Project tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.