Zendesk MCP Server
Enables comprehensive management of Zendesk tickets, comments, and Help Center articles through tools for searching, creating, and updating content. It includes specialized prompts for ticket analysis and response drafting to streamline support workflows.
README
Zendesk MCP Server
A Model Context Protocol server for Zendesk.
Note: This is a fork of reminia/zendesk-mcp-server with the following additions:
search_ticketstool for searching tickets by text, filters, custom fields, and date ranges
This server provides a comprehensive integration with Zendesk. It offers:
- Tools for retrieving and managing Zendesk tickets and comments
- Ticket search with support for custom fields, filters, and date ranges
- Specialized prompts for ticket analysis and response drafting
- Full access to the Zendesk Help Center articles as knowledge base

Prerequisites
-
uv - Python package manager (required)
Install uv if you don't have it:
# macOS/Linux curl -LsSf https://astral.sh/uv/install.sh | sh # Or with Homebrew brew install uv
Setup
-
Clone the repository and note the full path (you'll need it for configuration):
git clone <repo-url> /path/to/zendesk-mcp-server -
Build the project:
cd /path/to/zendesk-mcp-server uv venv && uv pip install -e . -
Configure Zendesk credentials in a
.envfile:cp .env.example .env # Edit .env with your Zendesk subdomain, email, and API key -
Configure in Claude Desktop (or Claude Code):
Add to your MCP settings, replacing
/path/to/zendesk-mcp-serverwith the absolute path to where you cloned the repo:
{
"mcpServers": {
"zendesk": {
"command": "uv",
"args": [
"--directory",
"/path/to/zendesk-mcp-server",
"run",
"zendesk"
]
}
}
}
Example paths:
- macOS:
/Users/yourname/dev/zendesk-mcp-server - Linux:
/home/yourname/projects/zendesk-mcp-server - Windows:
C:\\Users\\yourname\\dev\\zendesk-mcp-server
zendesk-help Skill
The zendesk-help skill provides tools for searching and managing Zendesk tickets. If you upload the SKILL.md file to Claude Desktop, you can use the zendesk-help skill to search for tickets and manage them. This will make claude's use of the zendesk-mcp-server more seamless.
Resources
- zendesk://knowledge-base, get access to the whole help center articles.
Prompts
analyze-ticket
Analyze a Zendesk ticket and provide a detailed analysis of the ticket.
draft-ticket-response
Draft a response to a Zendesk ticket.
Tools
get_tickets
Fetch the latest tickets with pagination support
-
Input:
page(integer, optional): Page number (defaults to 1)per_page(integer, optional): Number of tickets per page, max 100 (defaults to 25)sort_by(string, optional): Field to sort by - created_at, updated_at, priority, or status (defaults to created_at)sort_order(string, optional): Sort order - asc or desc (defaults to desc)
-
Output: Returns a list of tickets with essential fields including id, subject, status, priority, description, timestamps, and assignee information, along with pagination metadata
get_ticket
Retrieve a Zendesk ticket by its ID
- Input:
ticket_id(integer): The ID of the ticket to retrieve
get_ticket_comments
Retrieve all comments for a Zendesk ticket by its ID
- Input:
ticket_id(integer): The ID of the ticket to get comments for
create_ticket_comment
Create a new comment on an existing Zendesk ticket
- Input:
ticket_id(integer): The ID of the ticket to comment oncomment(string): The comment text/content to addpublic(boolean, optional): Whether the comment should be public (defaults to true)
create_ticket
Create a new Zendesk ticket
- Input:
subject(string): Ticket subjectdescription(string): Ticket descriptionrequester_id(integer, optional)assignee_id(integer, optional)priority(string, optional): one oflow,normal,high,urgenttype(string, optional): one ofproblem,incident,question,tasktags(array[string], optional)custom_fields(array[object], optional)
update_ticket
Update fields on an existing Zendesk ticket (e.g., status, priority, assignee)
- Input:
ticket_id(integer): The ID of the ticket to updatesubject(string, optional)status(string, optional): one ofnew,open,pending,on-hold,solved,closedpriority(string, optional): one oflow,normal,high,urgenttype(string, optional)assignee_id(integer, optional)requester_id(integer, optional)tags(array[string], optional)custom_fields(array[object], optional)due_at(string, optional): ISO8601 datetime
search_tickets
Search Zendesk tickets using query syntax with support for text search, filters, custom fields, and date ranges.
-
Input:
query(string, optional): Text to search in subject/descriptionstatus(string, optional): Filter by status -new,open,pending,hold,solved,closedpriority(string, optional): Filter by priority -low,normal,high,urgentassignee(string, optional): Filter by assignee emailrequester(string, optional): Filter by requester emailtags(array[string], optional): Filter by tagscustom_field_id(integer, optional): Custom field ID to searchcustom_field_value(string, optional): Value to match in custom fieldcreated_after(string, optional): ISO date - tickets created after this datecreated_before(string, optional): ISO date - tickets created before this datesort_by(string, optional): Field to sort by -created_at,updated_at,priority,status(defaults toupdated_at)sort_order(string, optional): Sort order -ascordesc(defaults todesc)limit(integer, optional): Max results, up to 100 (defaults to 25)
-
Output: Returns matching tickets with id, subject, status, priority, description, timestamps, assignee info, and tags, along with search metadata
-
Example - Search by custom field (e.g., transfer ID):
{ "custom_field_id": 23301179390491, "custom_field_value": "txn_abc123" }
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。