Zendesk-Talk
The Zendesk-Talk agent connector is a Python package that equips AI agents to interact with Zendesk-Talk through strongly typed, well-documented tools. It's ready to use directly in your Python app, in an agent framework, or exposed through an MCP.
Connector for the Zendesk Talk (Voice) API. Provides access to phone numbers, addresses, greetings, IVR configurations, call data, and agent/account statistics for Zendesk Talk voice support channels.
Example questions
The Zendesk-Talk connector is optimized to handle prompts like these.
- List all phone numbers in our Zendesk Talk account
- Show all addresses on file
- List all IVR configurations
- Show all greetings
- List greeting categories
- Show agent activity statistics
- Show the account overview stats
- Show current queue activity
- Which phone numbers have SMS enabled?
- Find agents who have missed the most calls today
- What is the average call duration across all calls?
- Which phone numbers are toll-free?
Unsupported questions
The Zendesk-Talk connector isn't currently able to handle prompts like these.
- Create a new phone number
- Delete an IVR configuration
- Update a greeting
- Make an outbound call
Installation
uv pip install airbyte-agent-zendesk-talk
Usage
Connectors can run in open source or hosted mode.
Open source
In open source mode, you provide API credentials directly to the connector.
from airbyte_agent_zendesk_talk import ZendeskTalkConnector
from airbyte_agent_zendesk_talk.models import ZendeskTalkApiTokenAuthConfig
connector = ZendeskTalkConnector(
auth_config=ZendeskTalkApiTokenAuthConfig(
email="<Your Zendesk account email address>",
api_token="<Your Zendesk API token from Admin Center>"
)
)
@agent.tool_plain # assumes you're using Pydantic AI
@ZendeskTalkConnector.tool_utils
async def zendesk_talk_execute(entity: str, action: str, params: dict | None = None):
return await connector.execute(entity, action, params or {})
Hosted
In hosted mode, API credentials are stored securely in Airbyte Cloud. You provide your Airbyte credentials instead.
If your Airbyte client can access multiple organizations, also set organization_id.
This example assumes you've already authenticated your connector with Airbyte. See Authentication to learn more about authenticating. If you need a step-by-step guide, see the hosted execution tutorial.
from airbyte_agent_zendesk_talk import ZendeskTalkConnector, AirbyteAuthConfig
connector = ZendeskTalkConnector(
auth_config=AirbyteAuthConfig(
customer_name="<your_customer_name>",
organization_id="<your_organization_id>", # Optional for multi-org clients
airbyte_client_id="<your-client-id>",
airbyte_client_secret="<your-client-secret>"
)
)
@agent.tool_plain # assumes you're using Pydantic AI
@ZendeskTalkConnector.tool_utils
async def zendesk_talk_execute(entity: str, action: str, params: dict | None = None):
return await connector.execute(entity, action, params or {})
Full documentation
Entities and actions
This connector supports the following entities and actions. For more details, see this connector's full reference documentation.
| Entity | Actions |
|---|---|
| Phone Numbers | List, Get, Context Store Search |
| Addresses | List, Get, Context Store Search |
| Greetings | List, Get, Context Store Search |
| Greeting Categories | List, Get, Context Store Search |
| Ivrs | List, Get, Context Store Search |
| Agents Activity | List, Context Store Search |
| Agents Overview | List, Context Store Search |
| Account Overview | List, Context Store Search |
| Current Queue Activity | List, Context Store Search |
| Calls | List, Context Store Search |
| Call Legs | List, Context Store Search |
Authentication
For all authentication options, see the connector's authentication documentation.
Zendesk-Talk API docs
See the official Zendesk-Talk API reference.
Version information
- Package version: 0.1.16
- Connector version: 1.0.2
- Generated with Connector SDK commit SHA: c5258debd165ab701252c1436d4acfb475bf92b9
- Changelog: View changelog
Metadata
Release files for airbyte-agent-zendesk-talk 0.1.16
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| airbyte_agent_zendesk_talk-0.1.16.tar.gz | 186.4 kB | Without provenance | Details for airbyte_agent_zendesk_talk-0.1.16.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| airbyte_agent_zendesk_talk-0.1.16-py3-none-any.whl | Python 3 | none | any | Details for airbyte_agent_zendesk_talk-0.1.16-py3-none-any.whl |
Total release size: 394.7 kB
Release files / airbyte_agent_zendesk_talk-0.1.16.tar.gz
| Download URL | airbyte_agent_zendesk_talk-0.1.16.tar.gz |
|---|---|
| Size | 186.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
03a783c7ab2be8276173f4f1d3435225ec292344b33c2c16b286625dca9fa0cc
|
|
BLAKE2b-256 checksum How to use checksums |
3184f89b56ab1c0b71a3e60121ebb4194290c9fa278efa4028768c0dc1793e4c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.12
|
Release files / airbyte_agent_zendesk_talk-0.1.16-py3-none-any.whl
| Download URL | airbyte_agent_zendesk_talk-0.1.16-py3-none-any.whl |
|---|---|
| Size | 208.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
187f3b0d569aedb5a0324d949b141facf1d387abed6fc991357b43dd8f3200a7
|
|
BLAKE2b-256 checksum How to use checksums |
b48f38ae7f481b9cbebc7ae77869d1ab7f2369f8c7ec51c8fbaa6c063684b1dc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.12
|
Security for airbyte-agent-zendesk-talk 0.1.16
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.