# Chatbase integrations: agents and conversations

> Create an agent, export conversations and create a source in Chatbase, and start a workflow when Chatbase sends “Lead submitted”.

**Canonical page:** https://tray.ai/connectors/chatbase-integrations/
**Categories:** AI
**Connects through:** HTTP Connector

## Overview

Chatbase builds AI support agents trained on a company's own documents and web pages, then deploys them to websites, WhatsApp, Slack, phone and helpdesk tools. Tray.ai connects to Chatbase through the HTTP Connector, so your workflows can call the Chatbase API alongside the rest of your stack.

## Use cases

### Agents

Read, create, update, delete, and manage agents in Chatbase from any Tray.ai workflow. The Chatbase API covers calls such as list agents and create an agent.

- List agents
- Create an agent
- Update an agent

### Conversations

Read conversations in Chatbase from any Tray.ai workflow. The Chatbase API covers calls such as list conversations and search conversations.

- List conversations
- Search conversations
- Export conversations

### Sources

Read, create, update, and delete sources in Chatbase from any Tray.ai workflow. The Chatbase API covers calls such as list sources and create a source.

- List sources
- Create a source
- Update a source

### Tickets

Read, create, and update tickets in Chatbase from any Tray.ai workflow. The Chatbase API covers calls such as list tickets and create a ticket.

- List tickets
- Create a ticket
- Update a ticket

### Contacts

Read, create, update, and delete contacts in Chatbase from any Tray.ai workflow. The Chatbase API covers calls such as create contacts and get a contact.

- Create contacts
- Get a contact
- Update a contact

### Chatbase events

Start a Tray.ai workflow the moment something happens in Chatbase. Chatbase sends events such as lead submitted and custom form submitted to a Tray.ai webhook trigger.

- Lead submitted
- Custom form submitted
- Collected data submitted

## Challenges Tray.ai solves

### Keeping Chatbase credentials out of logs

A raw API call usually means pasting a key or token into the request, where it ends up in step inputs, logs, and screenshots.

**How Tray.ai helps:** Store Chatbase credentials once as a Tray.ai authentication and reference them from the HTTP Connector. Tray.ai masks authentication values in logs, so the secret never shows up in a step's input or output.

### Going from the Chatbase API docs to a working call

Translating an example request from API docs into a workflow step means copying the method, URL, headers, and body by hand.

**How Tray.ai helps:** Paste a cURL example from the Chatbase API docs into the HTTP Connector and Tray.ai fills in the method, URL, headers, and body for you.

### Handling files and non-JSON responses

Not every API answers in JSON. Some return XML, files, or binary data, or expect a multipart upload.

**How Tray.ai helps:** The HTTP Connector parses JSON and XML responses, returns files you can pass to the next step, and sends multipart form data for uploads.

## Frequently asked questions

### Does Tray.ai connect to Chatbase?

Yes. Tray.ai connects to Chatbase through the HTTP Connector, which calls the Chatbase API directly. Any call the Chatbase API documents can run as a step in a Tray.ai workflow.

### How does Tray.ai authenticate with Chatbase?

The Chatbase API uses a bearer token. You save it once as a Tray.ai authentication, and the HTTP Connector adds it to every request.

### Can I get a dedicated Chatbase connector?

Chatbase runs through the HTTP Connector rather than a dedicated connector. If your team wants one, the Tray.ai connector SDK can build a dedicated Chatbase connector from the Chatbase API.

## Learn more

- Intelligent Integration: https://tray.ai/platform/intelligent-ipaas/
- Merlin Agent Builder: https://tray.ai/platform/merlin-agent-builder/
- Agent Gateway for MCP: https://tray.ai/platform/agent-gateway/
- Book a demo: https://tray.ai/contact/