Create a Connector

Create a Custom Connector to give an AI Fellow access to a specific action or information in another system. Define what it should do and when the Fellow should use it, then work with your IT team to provide the connection address (endpoint), authentication token, and required fields. You can reuse the saved Connector across AI Fellows and Learning Paths.

Owners, Full Admins, and Creators can create custom Connectors. Managers cannot open the Connectors Library. The setup steps below cover the form; the response-format section provides the technical details your IT team needs.

Fixed field valuesCopy Anchor Link

Sometimes a field should always carry the same value rather than something the AI Fellow asks the user for, such as an account type, a region, or a setting that never changes for this Connector. Turn on Always send a fixed value on the field, then enter the value.

When a field has a fixed value:

• The AI Fellow never sees or asks for it. Frontierz adds the value to every call, and it cannot be changed during a conversation.
• The value is sent in the format that matches the field type, so a Yes/No field sends a yes/no value and a number field sends a number.
• The Optional setting no longer applies, since the field is always filled.

This is more dependable than asking for the value in the field description, which the AI Fellow may skip or send in the wrong format. Fixed values apply to fields you add yourself; fields that an MCP connection brought in automatically cannot be set this way.

Choose how the Connector signs inCopy Anchor Link

The Authentication section applies to both Webhook and MCP Server Connectors.

• Bearer token sends a fixed token with every request, or nothing if you leave the field empty. Use it when the receiving system gives you an API key or token.
• OAuth 2.0 signs in to the service once through its own approval page. Frontierz then keeps the access token and refreshes it automatically.

OAuth 2.0 uses the authorization code flow with PKCE, so someone with an account in the other service approves access in the browser. Services that only offer the client credentials flow, used for machine-to-machine access, need a Bearer token instead.

To set up OAuth 2.0, your IT team first creates an OAuth app in the other service. Then:

The client secret and tokens are stored encrypted, and the secret is not shown again after you save it. Leave the field blank to keep the saved secret.

If the service stops accepting the refresh, the status changes to Reconnect needed and the Connector does not call the service until an administrator clicks Reconnect. Changing the authorization URL, token URL, client ID, scopes, or endpoint also requires you to connect again. Disconnect removes the saved tokens.

Customize the request bodyCopy Anchor Link

By default, a Webhook Connector sends a standard JSON payload with the Connector's name, its identifiers, the collected fields under fields, and the user's identifier. If the receiving system expects a different format, open Customize request body in Endpoint Configuration and write the JSON it should receive instead. Leave Request body (optional) empty to keep the standard payload. MCP Server Connectors do not use this option.

Write {{field_key}} wherever a field's value belongs. Available fields: lists the keys of this Connector's fields. For example:

{
  "ticket": {
    "subject": "{{subject}}",
    "priority": "{{priority}}",
    "description": "Reported by {{user.name}}: {{details}}"
  }
}

• A placeholder that is the whole value, such as "{{priority}}", is replaced by the value in its own type: a number stays a number, and a Yes/No field becomes true or false. A missing optional value is sent as null.
• A placeholder inside other text is replaced as text. A missing value becomes empty text.
• Fixed field values are included the same way.
• The request is always sent with POST as JSON. The custom body replaces the whole standard payload, so include any identifiers your system needs.

The body must be a valid JSON object or array of no more than 20,000 characters, and it can use only this Connector's fields. Studio rejects the body when it is invalid or uses a field the Connector does not have.

Include the user's name and emailCopy Anchor Link

Two more placeholders add details of the person talking to the AI Fellow: {{user.email}} and {{user.name}}. Frontierz fills them from the signed-in account, not from the conversation, so the AI Fellow cannot change them. For guests without an account, such as people using a public link, they are empty. In a test run, they contain your own details.

What the endpoint should returnCopy Anchor Link

For the IT team configuring the receiving service: the endpoint must return a JSON response. An HTTP status in the 2xx range records the call as successful; a 4xx or 5xx status records it as failed. Include the information the Fellow needs to explain the result to the user or pass to another Connector.

Put the result in a message field. The AI Fellow treats message as the summary of the call and can read it back to the user. A data field works the same way.

{ "message": "Ticket INC0203044 is open and assigned to the support team." }

If the response has no message and no data field, the AI Fellow receives the whole JSON body instead, so the individual fields are still available. This matters when one Connector feeds another. A user lookup that returns this:

{ "userName": "Alex Rivera", "userEmail": "alex.rivera@example.com" }

gives the AI Fellow the email, which it can then pass into a second Connector, such as one that lists that user's open tickets.

When a call fails, return an error field with a short reason. The AI Fellow reads that back instead of a generic failure message.

{ "error": "No user found for that email address." }

Test the Connector before publicationCopy Anchor Link

Once the Connector is saved, a real call can be sent to the endpoint without starting a voice session.

If the test fails, ask the team responsible for the receiving system to check the endpoint URL, authentication token, and required fields against the request and response in the log.

Use it in AI Fellows and Learning PathsCopy Anchor Link

Once the Connector exists, attach it from either side:

• From an AI Fellow, to make it available in that AI Fellow’s conversations.
• From a Learning Path, to make it available across every session in the Learning Path.