conversation_ai_create_agent

Create an Agent

SERVERGhl SOURCE@aiwerk/mcp-server-ghl

Medium RISK CLASS

Category Write

Parameters 124 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/aiwerk-mcp-server-ghl/conversation-ai-create-agent.md

WHAT IT DOES

What conversation_ai_create_agent does on Ghl

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

Parameter	Type	Required	Description
`goal`	string	Yes	The goal of the agent.
`mode`	string	—	Mode of operation - OFF, SUGGESTIVE, or AUTO_PILOT
`name`	string	Yes	Name of the agent.
`channels`	array	—	Communication channels the agent can operate on
`waitTime`	number	—	Wait time before agent responds (max 5 for minutes, 300 for seconds)
`isPrimary`	boolean	—	Indicates if this agent is a primary agent.
`sleepTime`	number	—	Duration of sleep period (required if sleepEnabled is true). Set to null for indefinite sleep. (max 2880 for minutes, 172800 for seconds, 48 for hours)
`personality`	string	Yes	Personality traits of the agent.
`businessName`	string	—	Name of the business the agent represents.
`instructions`	string	Yes	Instructions for the agent.
`sleepEnabled`	boolean	—	Indicates if sleep functionality is enabled.
`waitTimeUnit`	string	—	Unit for wait time - SECONDS or MINUTES

Parameters from the server's own tool schema.

RISK

Why conversation_ai_create_agent is rated Medium

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

Risk signalsHigh parameter count (19 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs conversation_ai_create_agent safely

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

conversation_ai_create_agent Rate-limited

conversation_ai_create_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": {
    "conversation_ai_create_agent": {
      "limits": [
        {
          "counter": "conversation_ai_create_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 Ghl, apply this rule, and every conversation_ai_create_agent call is checked against it from then on.

FAQ

Questions about conversation_ai_create_agent

What does the conversation_ai_create_agent tool do? +

Create an Agent. It is categorised as a Write tool in the Ghl MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does conversation_ai_create_agent accept? +

conversation_ai_create_agent accepts 12 parameters: goal, mode, name, channels, waitTime, isPrimary, sleepTime, personality, businessName, instructions, sleepEnabled, waitTimeUnit. Required: goal, name, personality, instructions. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on conversation_ai_create_agent? +

Register the Ghl MCP server in PolicyLayer and add a rule for conversation_ai_create_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 Ghl. Nothing to install.

What risk level is conversation_ai_create_agent? +

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

Can I rate-limit conversation_ai_create_agent? +

Yes. Add a rate_limit block to the conversation_ai_create_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 conversation_ai_create_agent completely? +

Set action: deny in the PolicyLayer policy for conversation_ai_create_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 conversation_ai_create_agent? +

conversation_ai_create_agent is provided by the Ghl MCP server (@aiwerk/mcp-server-ghl). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Ghl, and thousands of servers like it.

This server

All 569 Ghl 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 →