agent_studio_execute_agent

Execute Agent

SERVERGhl SOURCE@aiwerk/mcp-server-ghl

High RISK CLASS

Category Execute

Parameters 92 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/agent-studio-execute-agent.md

WHAT IT DOES

What agent_studio_execute_agent does on Ghl

AI agents invoke agent_studio_execute_agent to trigger actions in Ghl. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Parameter	Type	Required	Description
`source`	string	—
`agentId`	string	Yes
`message`	string	Yes	Message to send to the agent
`contactId`	string	—	Contact ID to associate with this execution. When provided, contact data will be hydrated and made available to the agent.
`versionId`	string	—	Published version ID to execute. If not provided, the latest published production version will be used.
`locationId`	string	—	Location ID Defaults to GHL_LOCATION_ID when omitted.
`attachments`	array	—	Attachments for the message
`executionId`	string	—	Unique session identifier that maintains conversational context across multiple interactions within the same agent session. Omit this field for the first messag
`inputVariables`	object	—	Input variables to pass to the agent. These should match the input variables defined in the agent configuration.

Parameters from the server's own tool schema.

RISK

Why agent_studio_execute_agent is rated High

agent_studio_execute_agent triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs agent_studio_execute_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 agent_studio_execute_agent, this is the rule to start with:

agent_studio_execute_agent Rate-limited

agent_studio_execute_agent stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "agent_studio_execute_agent": {
      "limits": [
        {
          "counter": "agent_studio_execute_agent_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about agent_studio_execute_agent

What does the agent_studio_execute_agent tool do? +

Execute Agent. It is categorised as a Execute tool in the Ghl MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does agent_studio_execute_agent accept? +

agent_studio_execute_agent accepts 9 parameters: source, agentId, message, contactId, versionId, locationId, attachments, executionId, inputVariables. Required: agentId, message. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on agent_studio_execute_agent? +

Register the Ghl MCP server in PolicyLayer and add a rule for agent_studio_execute_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 agent_studio_execute_agent? +

agent_studio_execute_agent is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit agent_studio_execute_agent? +

Yes. Add a rate_limit block to the agent_studio_execute_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 agent_studio_execute_agent completely? +

Set action: deny in the PolicyLayer policy for agent_studio_execute_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 agent_studio_execute_agent? +

agent_studio_execute_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 → High-risk tools on this server →

Across the catalogue

claude_execute on Claude Bridge →execute_test_case on Percepta MCP Server → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →