MCP server with n8n
How do I set up an MCP server with n8n?
n8n is a workflow automation platform that lets you build an MCP server without deep programming knowledge. Each tool call from your AI agent is mapped as its own n8n workflow.
Prerequisite: You need a running n8n instance (self-hosted or n8n Cloud) as well as basic familiarity with the n8n interface.
Step 1: Create an MCP server workflow
Open your n8n instance and create a new workflow.
Select the MCP Server Trigger.
n8n automatically generates a webhook URL for your MCP server — make a note of it, you will need it later in sipgate.
Tip: Also secure your MCP server workflow with a token. To do this, enable Bearer or Header authentication in the MCP Server Trigger and assign a token. This way, only sipgate can communicate with your server.
Step 2: Define tools as workflows
A tool is a single capability that your AI agent can use during a conversation, such as looking up a customer number, checking availability, or booking an appointment. Each tool corresponds exactly to one n8n workflow: the agent decides during the conversation when it needs a tool, and n8n executes the underlying logic.
Each tool that your AI agent should use is created as a separate workflow:
Create a new workflow for each tool.
Also use the MCP Server Trigger as the starting point.
Build the desired logic behind it: database queries, API calls, calculations.
At the end of the workflow, return a structured result that the AI agent can use.
Tip: Keep each workflow focused on a single, clearly defined task. Simple, deterministic workflows are more reliable than complex branching.
Step 3: Store tool descriptions in n8n
So that the AI agent knows when to use which tool, you need to store descriptions in n8n:
Tool name: Assign a unique, descriptive name — maximum 28 characters.
Tool description: Explain in 1–2 sentences what the tool does and when it should be used.
Parameter descriptions: Describe each parameter: what is expected, in what format, and whether it is optional.
Example of a good tool description:
“Returns the customer's full name and customer number. Input: phone number in the format +49…”
Step 4: Add the MCP server in sipgate
Copy the webhook URL of your n8n MCP workflow.
In app.sipgate.com, open your AI agent → Integrations → Live call features → Add.
Enter the URL. If you assigned a token in n8n, enter it in the Token (optional) field.
Save. sipgate checks the connection and shows you the detected tools.
Test the MCP server
Before using the AI agent in production, we recommend the following tests:
Check connection status: Open the Live Call Features overview in sipgate and refresh the connection to the MCP server. If all tools are loaded, the connection is successful.
Manual test calls: Trigger the playbook manually and check in n8n whether the workflows are called correctly and the responses are correct.
Check server logs: Look in the n8n execution logs to see whether requests are arriving and whether errors have occurred.
Error handling: Make sure your workflow returns a clear error message in case of failure — the AI agent uses this to adapt its behavior.
Tip: Design your error messages so that the AI agent can infer what went wrong and whether it should try again.
Best practices
Use n8n for deterministic tasks: retrieve data, write data, calculate.
Leave the non-deterministic decisions: what it does, in what order, how it responds.
Validate all incoming parameters server-side — the AI agent does not always pass exactly what you expect.
Return clean, structured responses. Unclear returns lead to unreliable agent behavior.
Last updated