n8n, Make, Zapier

Low-code platforms like n8n, Make, and Zapier don’t ship a native TapPass node — but they don’t need one. TapPass exposes an OpenAI-compatible HTTP endpoint; a generic HTTP node is enough.

Common config

Field	Value
Method	POST
URL	https://tappass.example.com/v1/chat/completions
Auth	Bearer tp_...
Headers	Content-Type: application/json
Body	OpenAI chat completion payload

Example body:

{
  "model": "gpt-4o-mini",
  "messages": [
    { "role": "user", "content": "{{ $json.prompt }}" }
  ]
}

n8n

1. Add an HTTP Request node.
2. Method: POST. URL: https://tappass.example.com/v1/chat/completions.
3. Authentication → Generic Credential → Header Auth:
   • Name: Authorization
   • Value: Bearer tp_...
4. Body: JSON, with the payload above (Reference the previous node with {{ $json.prompt }}).
5. Run. The output has the standard OpenAI response shape.

tappass-examples/n8n

Make (Integromat)

1. Add an HTTP → Make a request module.
2. URL, method, headers, body as above.
3. Map the previous module’s output into the messages field.

tappass-examples/make

Zapier

1. New action → Webhooks by Zapier → Custom Request.
2. Method: POST. URL + headers + body as above.
3. Parse the response JSON and pull choices[0].message.content.

tappass-examples/zapier

What you get

Every low-code automation that hits the endpoint:

• Runs through the full governance pipeline
• Appears in the audit trail with agent_id you set via header
• Enforces the same policy, budgets, and PII rules as SDK calls

Per-automation identity

Add a header so you can filter audit events per workflow:

X-Agent-Id: n8n-support-bot