Run a single payload test from a workflow config JSON file.
AI agents invoke test_workflow to trigger actions in N8n Workflow Tester Safe. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a workflow with a given payload, triggering external operations whose effects depend on the workflow's content and arguments. Running workflows can invoke external APIs, send messages, modify systems, etc. The 'safe' server description notes no credential management but workflows can still trigger real operations, making this high severity.
From the tool's definition "Run a single payload test from a workflow config JSON file"
Attacks that exploit this kind of access
Run a single payload test from a workflow config JSON file. It is categorised as a Execute tool in the N8n Workflow Tester Safe MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the N8n Workflow Tester Safe MCP server in PolicyLayer and add a rule for test_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 Workflow Tester Safe. Nothing to install.
test_workflow is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the test_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 test_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.
test_workflow is provided by the N8n Workflow Tester Safe MCP server (souzix76/n8n-workflow-tester-safe). 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 →