AI agents use create-flow to create or update resources in Node Red — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Node Red environment.
Creating a flow in Node-RED adds new automation/workflow configurations to the system. This is a reversible Write operation (flows can be deleted or modified). Severity is medium because a malicious flow could potentially trigger unintended automation, but the impact depends on what the flow does and the environment's security controls.
From the tool's definition Tool name 'create-flow' indicates creation of a new flow in Node-RED, which is a data creation operation. Description is empty, but the name clearly maps to flow creation functionality.
Attacks that exploit this kind of access
create-flow. It is categorised as a Write tool in the Node Red MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Node Red MCP server in PolicyLayer and add a rule for create-flow: 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 Node Red. Nothing to install.
create-flow 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-flow 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-flow. 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-flow is provided by the Node Red MCP server (node-red-mcp-server). 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 →