Zendesk API MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 49 tools
Every tool has a clearly distinct purpose targeting specific Zendesk resources (articles, tickets, users, etc.) with specific actions (create, get, list, update, delete). The naming convention makes it impossible to confuse tools since each combination of verb and resource name is unique and unambiguous.
All 49 tools follow a perfectly consistent verb_noun pattern with snake_case throughout. The verbs (create, get, list, update, delete, search, support_info) are applied systematically across resources, creating a predictable and readable naming scheme.
With 49 tools, this server feels excessively heavy for typical MCP usage. While Zendesk has many resource types, the tool count suggests over-fragmentation where a more consolidated approach might be more agent-friendly. This many tools will likely overwhelm agents and increase misselection risk.
The tool surface provides comprehensive CRUD coverage for all major Zendesk resources (articles, automations, groups, macros, organizations, tickets, triggers, users, views) plus listing operations, search, and support info. There are no obvious gaps for the customer support domain this server targets.