create_ai_agent

SERVERTimeweb SOURCEtimeweb-mcp

Medium RISK CLASS

Category Write

Parameters 125 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/timeweb-mcp/create-ai-agent.md

WHAT IT DOES

What create_ai_agent does on Timeweb

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

Parameter	Type	Required	Description
`name`	string	Yes	ОБЯЗАТЕЛЬНОЕ ПОЛЕ - название агента
`top_p`	number	—	top_p модели
`model_id`	number	Yes	ОБЯЗАТЕЛЬНОЕ ПОЛЕ - ID модели (см. list_ai_models)
`max_tokens`	number	—	Максимум токенов в ответе
`project_id`	number	—	ID проекта
`access_type`	string	Yes	ОБЯЗАТЕЛЬНОЕ ПОЛЕ - тип доступа: public или private
`description`	string	—	Описание агента
`temperature`	number	—	temperature модели
`refine_query`	boolean	—	Уточнять ли запрос перед обработкой (по умолчанию false)
`system_prompt`	string	Yes	ОБЯЗАТЕЛЬНОЕ ПОЛЕ - системный промпт агента
`presence_penalty`	number	—	presence_penalty
`token_package_id`	number	Yes	ОБЯЗАТЕЛЬНОЕ ПОЛЕ - ID пакета токенов (см. list_ai_agent_token_packages)

Parameters from the server's own tool schema.

RISK

Why create_ai_agent is rated Medium

An AI agent can call create_ai_agent faster than any human can review: one bad instruction and it creates or modifies resources in Timeweb by the hundred, each call as confident as the last.

Risk signalsHigh parameter count (13 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs create_ai_agent safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Timeweb, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For create_ai_agent, this is the rule to start with:

create_ai_agent Rate-limited

create_ai_agent stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_ai_agent": {
      "limits": [
        {
          "counter": "create_ai_agent_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Timeweb, apply this rule, and every create_ai_agent call is checked against it from then on.

FAQ

Questions about create_ai_agent

What does the create_ai_agent tool do? +

Создаёт нового AI-агента. Обязательны: name, access_type, model_id, token_package_id, system_prompt. Перед вызовом получи model_id через list_ai_models и token_package_id через list_ai_agent_token_packages. It is categorised as a Write tool in the Timeweb MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does create_ai_agent accept? +

create_ai_agent accepts 12 parameters: name, top_p, model_id, max_tokens, project_id, access_type, description, temperature, refine_query, system_prompt, presence_penalty, token_package_id. Required: name, model_id, access_type, system_prompt, token_package_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on create_ai_agent? +

Register the Timeweb MCP server in PolicyLayer and add a rule for create_ai_agent: 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 Timeweb. Nothing to install.

What risk level is create_ai_agent? +

create_ai_agent is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_ai_agent? +

Yes. Add a rate_limit block to the create_ai_agent 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.

How do I block create_ai_agent completely? +

Set action: deny in the PolicyLayer policy for create_ai_agent. 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.

What MCP server provides create_ai_agent? +

create_ai_agent is provided by the Timeweb MCP server (timeweb-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Timeweb, and thousands of servers like it.

This server

All 245 Timeweb tools →

Across the catalogue

create_task on 0rca Dojo MCP Server →create-task on Kanban MCP Server →create_package_backup on Android Forensics ADB MCP Server →create_project on Stitch MCP Server → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →