AI agents use update-flows 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.
This tool creates or modifies flow definitions in Node-RED, which are reversible changes (flows can be reverted or re-edited). It does not delete data (which would be Destructive) or execute arbitrary code (which would be Execute). High severity because misconfigured flows could disrupt automation, affect dependent systems, or trigger unintended actions.
From the tool's definition Tool name is 'update-flows'; no description provided. In Node-RED context, 'flows' are the core automation/logic definitions. The 'update' operation modifies existing flows, making this a Write action.
Attacks that exploit this kind of access
update-flows. 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 update-flows: 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.
update-flows 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 update-flows 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 update-flows. 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.
update-flows 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 →