create_workflow_and_activate

THE RISK

High Risk

Why create_workflow_and_activate needs a policy

This tool not only writes a new workflow (Write) but also activates it, meaning it will begin executing — potentially triggering webhooks, scheduled jobs, API calls, or other external operations. The activation step elevates this beyond Write into Execute territory, with high severity since an AI agent could deploy and run arbitrary automation workflows with broad external effects.

From the tool's definition 'Create and activate an n8n workflow' — the tool both creates a workflow and immediately activates it, triggering external operations

Documented attack patterns abuse exactly the kind of access create_workflow_and_activate gives an agent:

POLICY

How to control create_workflow_and_activate

PolicyLayer is an MCP gateway — it sits between your AI agents and n8n Workflow Builder MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_workflow_and_activate:

policy.json

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

create_workflow_and_activate 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.

Create a free account and register n8n Workflow Builder MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More n8n Workflow Builder MCP Server tools

Destructive delete_credential Delete a credential by ID. This will remove the credential and make it unavailable for wor Destructive delete_execution Delete a workflow execution record from the n8n instance Destructive delete_tag Remove unused tags from the system Destructive delete_workflow Delete an n8n workflow Destructive remove_node Remove a node from a workflow (also removes its connections) Execute execute_workflow Trigger immediate execution of a workflow by its ID. Starts the workflow manually regardle Execute activate_workflow Activate an n8n workflow Write add_node Add a single node to an existing workflow

All 34 n8n Workflow Builder MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in n8n Workflow Builder MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about create_workflow_and_activate

What does the create_workflow_and_activate tool do? +

Create and activate an n8n workflow. It is categorised as a Execute tool in the n8n Workflow Builder MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on create_workflow_and_activate? +

Register the n8n Workflow Builder MCP Server MCP server in PolicyLayer and add a rule for create_workflow_and_activate: 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 n8n Workflow Builder MCP Server. Nothing to install.

What risk level is create_workflow_and_activate? +

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

Can I rate-limit create_workflow_and_activate? +

Yes. Add a rate_limit block to the create_workflow_and_activate 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_workflow_and_activate completely? +

Set action: deny in the PolicyLayer policy for create_workflow_and_activate. 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_workflow_and_activate? +

create_workflow_and_activate is provided by the n8n Workflow Builder MCP Server MCP server (makafeli/n8n-workflow-builder). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every n8n Workflow Builder MCP Server tool call.

Start from n8n Workflow Builder MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →