AI agents use create_variable to create or update resources in N8n — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your N8n environment.
This tool creates a new instance variable, which is a reversible write operation. It modifies the n8n automation system's configuration/state by adding a new variable, but does not delete, execute arbitrary code, or move money. The write_mode requirement shows it's gated as a write operation.
From the tool's definition Tool description explicitly states 'Create a new instance variable' - this is a create operation that adds new data to the n8n system. The requirement for 'write_mode' protection confirms it performs a reversible modification rather than a destructive action.
Attacks that exploit this kind of access
Create a new instance variable. Requires write_mode. It is categorised as a Write tool in the N8n 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 create_variable: 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. Nothing to install.
create_variable 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 create_variable 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 create_variable. 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.
create_variable is provided by the N8n MCP server (siddharth0903/n8n-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 →