Zendesk Connector

Zendesk is a customer service platform designed to foster better customer relationships through its comprehensive ticketing, support, and engagement.

Start for free View documentation

4.8 on G2

Weld · Data Sources

Zendesk

ZendeskYour warehouseLive

ticket48 columnsSynced

user48 columnsSynced

organization12 columnsSynced

group9 columnsSyncing

ticket_form15 columnsQueued

Lands in

snowflake

bigquery

databricks

Agent context over MCP

How it works

Set up in minutes.
No code, no maintenance.

Zendesk

Zendesk

Data source

Authenticating...

Ready to connect

Overview

Zendesk in your warehouse.
Ready for your agents.

Zendesk is a customer service platform designed to foster better customer relationships through its comprehensive ticketing, support, and engagement. Weld's Zendesk connector is fully managed: it extracts data from Zendesk, loads it into your warehouse, and keeps it in sync. The data lands in a clean, documented schema with agent context attached, so analysts can query it with SQL or dbt, and agents can query it over the Weld MCP server without guessing at tables or joins.

Agent context

Zendesk data schema.
The map your agents read.

Every table, field and relationship Weld syncs from Zendesk is served to agents as context over MCP, so they pick the right tables and join on the right keys.

tables: 43
fields: 444
relationships: 23

Loading diagram…

ticket_side_conversation

ticket_side_conversation_event

automation_action

automation_condition

has_help_center

help_center_state

brand_ticket_form

end_user_description

raw_agent_label

group_membership

organization_fields

shared_comments

organization_tag

organization_id

organization_domain_name

organization_id

organization_membership

organization_id

organization_name

sharing_agreement

custom_status_id

organization_id

allow_attachments

allow_channelback

attribute_value_ids

collaborator_ids

ticket_sharing_agreement

sharing_agreement_id

ticket_follower

ticket_collaborator

collaborator_id

ticket_custom_field

custom_field_id

agent_wait_time_in_minutes_business

agent_wait_time_in_minutes_calendar

assignee_stations

assignee_updated_at

custom_status_updated_at

first_resolution_time_in_minutes_business

ticket_activity

metadata_system_client

metadata_system_ip_address

metadata_system_latitude

metadata_system_location

ticket_comment_attachment

ticket_comment_id

malware_access_override

malware_scan_result

mapped_content_url

agent_description

collapsed_for_agents

creator_app_name

creator_user_id

editable_in_portal

system_ticket_field_option

ticket_field_id

custom_ticket_field_option

ticket_field_id

agent_conditions

end_user_conditions

end_user_visible

ticket_form_ticket_field

ticket_field_id

ticket_form_restricted_brand

restricted_brand_id

ticket_side_conversation

message_added_at

state_updated_at

ticket_side_conversation_external_id

ticket_side_conversation_id

ticket_side_conversation_participant

ticket_side_conversation_id

ticket_side_conversation_event

side_conversation_id

ticket_side_conversation_event_message_to

ticket_side_conversation_event_id

trigger_condition

trigger_category

organization_id

default_group_id

Open the schema explorer Open the full schema explorer

Models

Zendesk models.
What the numbers mean.

Open-source SQL that turns the raw Zendesk tables into the reports people ask about. Deploy them in Weld and your agent queries the definitions, not guesses.

Open the models

Weld MCP server

Ask your agent.
It already knows Zendesk.

Connect Claude, Cursor, ChatGPT or your own agent to Weld over MCP. It reads the Zendesk context, finds the tables it needs and queries your warehouse.

Agent contextZendesk tables, fields and joins
QuerySQL against your warehouse
OperateCheck, rerun and refresh syncs

Set up the MCP server

Claude CodeOpus 5

ConnectedWeld MCPAgent contextZendesktables43fields444joins23

>

How many ticket rows do we have per brand? Use our Zendesk data.

Reading the Zendesk context first, so the query uses the right tables and keys.

●weld·search_available_references

⎿raw.zendesk.ticket

raw.zendesk.brand

+ 41 more Zendesk tables

●weld·get_reference_schema

⎿ticket · 48 columns

joins brand on brand_id

●weld·run_query

⎿select b.id, count(*) from {{raw.zendesk.ticket}} t

join {{raw.zendesk.brand}} b on t.brand_id = b.id

group by 1

submitted

●weld·get_query_status

⎿DONE

●weld·get_query_result

⎿rows returned

✓Answered from Zendesk data in your warehouse

>Ask about your Zendesk dataMCP

Destinations

Load Zendesk into any warehouse.
Set up in minutes, no code.

Resources

Everything you need.
To get started.

Zendesk setup guide

Step-by-step instructions to configure and start syncing.

Connect your agents

Set up Claude, Cursor, ChatGPT or Codex against your Weld workspace.

Weld Connect API

Build custom connectors

Use the Weld Connect API to build and publish your own connector.

Common questions

Answers to frequently asked questions about Weld connectors.

Weld Connect API

Set it up in code.
One REST API.

Use the Weld Connect REST API to create Zendesk connections, configure ELT syncs, and manage pipelines entirely through code. Built for embedding, automation, and CI/CD workflows.

Explore Weld Connect API reference

POST/elt_syncs

# Create a Zendesk ELT sync
curl -X POST https://connect.weld.app/elt_syncs \
  -H "x-api-key: $API_KEY" \
  -d '{
    "connection_id": "conn_abc123",
    "integration_id": "zendesk",
    "destination_schema_name": "zendesk_data",
    "sync_interval": "0 * * * *"
  }'
▌

FAQ

Common questions.
About connectors.

Something not covered here? A data engineer can walk through your setup with you.

Put your Zendesk data to work.

Connect Zendesk, pick a warehouse, and your agents can query it today. Free for 14 days, no credit card.

Zendesk

Source

Weld

MCPAgents

Start for free Talk to us

Connectors

Explore more connectors.
300+ and counting.

View all connectors