Skip to main content
The Lorikeet MCP server allows AI tools like ChatGPT and Claude to access your Lorikeet account data directly, including workflows, tools, integrations, knowledge base articles, and more.
Looking to connect an external MCP server to Lorikeet as a tool provider? See the External MCP Servers page instead.
Once connected, you can:
  • Diagnose tickets - trace workflow execution and identify root causes
    “Pull up ticket #12345. What went wrong and why did the customer get escalated?”
  • Audit knowledge bases - analyze articles at scale, find gaps, and spot quality issues
    “Review all our knowledge base articles. Which ones are outdated, which topics have gaps, and are there any quality issues?”
  • Explore your setup - inspect workflows, tools, and integrations
    “Give me a summary of what integrations are configured.”
  • Build workflows - create and iterate on workflows using natural language
    “Create a new natural language workflow that handles refund requests by checking order status, verifying the return window, and processing the refund.”
  • Test tools - run and validate tool configurations directly from your AI assistant
    “Test the ‘get-order-status’ tool with order ID 98765 and check if the response matches what we expect.”
  • Run simulations - test workflows against different customer scenarios
    “Set up a simulation batch for the refund workflow with 3 different customer scenarios — a valid refund, an expired return window, and a missing order — and run it.”
MCP (Model Context Protocol) is an open standard for connecting AI tools to external data sources and services.

MCP server URL

Use a single, region-agnostic endpoint regardless of where your Lorikeet account is hosted:
Authentication routes traffic to your account’s region automatically.

Setup

Prerequisites

  • Access to ChatGPT with a Team, Business, or Enterprise subscription
  • Workspace Admin access is required for the initial setup (Steps 1–5). Once complete, all workspace members can use the app.

Connect

1

Open Workspace Settings

Go to chatgpt.com, click your profile icon in the bottom-left corner, and select Workspace settings.
2

Create a new app

In the admin panel, click the Create button.
3

Configure the app

Fill in the app configuration:
  • Name: Lorikeet
  • Description: Access your Lorikeet account.
  • MCP Server URL: https://mcp.lorikeetcx.ai
  • Authentication: Select OAuth
Click Create to proceed.
4

Authorize

You will be redirected to the Lorikeet authorization page. Sign in to your Lorikeet account and click Authorize.
5

Publish the app

After authorization, the Lorikeet app will appear in the Drafts section. Click on the app, then click Publish to make it available to your workspace.
6

Use the app

Workspace members can now use the Lorikeet app in their conversations:
  1. Start a new chat
  2. Click the + button near the message input
  3. Click More to see all available apps
  4. Select Lorikeet

Troubleshooting

For troubleshooting connection issues, refer to the ChatGPT apps docs.If you’re still having trouble, reach out to the Lorikeet team.

Non-interactive access

For headless clients that have no browser to complete the interactive login, such as cloud agents, CI jobs, and scheduled scripts, authenticate with the client credentials grant, the standard OAuth 2.1 flow for machine-to-machine (M2M) access. If your client needs a human at any point, use the interactive tabs above instead.
Tokens issued this way are read-only. They can read workflows, tools, tickets, and other config, but cannot create or modify anything. Use the interactive flow if you need write access.
1

Create an API key

Generate a client_id and client_secret pair with the Create an API key endpoint. The secret is shown once, so store it somewhere safe.
2

Exchange it for an access token

POST to the token endpoint https://mcp.lorikeetcx.ai/oauth/token with grant_type=client_credentials. Send the secret in the request body (client_secret_post), or via HTTP Basic (client_secret_basic).
The response returns an access token:
The client credentials grant does not issue a refresh token, so request a new token once the one-hour token expires.
3

Connect your client

Pass the token as Authorization: Bearer <token> to https://mcp.lorikeetcx.ai. Any MCP client accepts a bearer token; the tabs below show the idiomatic wiring.
Codex reads the bearer from an environment variable, so mint a token into it before launching:
Or in ~/.codex/config.toml:
Codex reads the token once at launch and does not refresh it. The token expires one hour after it is minted, so mint a fresh one before each run.

Technical details