AI agents use n8n_generate_workflow to create or update resources in n8n-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your n8n-MCP environment.
This tool creates a new workflow artifact based on a natural language prompt. Creation of workflows is a Write operation. Severity is high because AI-generated workflows could contain unintended automation logic, execute external calls, or trigger sensitive operations when later deployed — especially since sibling tools like n8n_deploy_template exist to activate them.
From the tool's definition Generate an n8n workflow from a natural language description using AI
Attacks that exploit this kind of access
Generate an n8n workflow from a natural language description using AI. It is categorised as a Write tool in the n8n-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the n8n- MCP server in PolicyLayer and add a rule for n8n_generate_workflow: 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-MCP. Nothing to install.
n8n_generate_workflow 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 n8n_generate_workflow 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 n8n_generate_workflow. 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.
n8n_generate_workflow is provided by the n8n- MCP server (spring1237/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →