🧠 AI-powered node suggestion based on workflow description.
AI agents call suggest_workflow_nodes to retrieve information from n8n Workflow Builder without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool takes a workflow description as input and suggests nodes to use. This is a recommendation/advisory operation that reads context and returns suggestions without modifying, executing, or deleting any data or workflows.
From the tool's definition 'suggest_workflow_nodes' and 'AI-powered node suggestion based on workflow description' — the tool analyzes a description and returns suggestions, implying a read/query operation with no side effects
Attacks that exploit this kind of access
🧠 AI-powered node suggestion based on workflow description. It is categorised as a Read tool in the n8n Workflow Builder MCP Server, which means it retrieves data without modifying state.
Register the n8n Workflow Builder MCP server in PolicyLayer and add a rule for suggest_workflow_nodes: 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. Nothing to install.
suggest_workflow_nodes is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the suggest_workflow_nodes 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 suggest_workflow_nodes. 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.
suggest_workflow_nodes is provided by the n8n Workflow Builder MCP server (schimmilab/n8n-workflow-builder). 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 →