No install? Use cloud.anythingmcp.com directly.
Sign in, install the Zendesk Support in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Drive Zendesk Support (the help-desk product) from any AI agent: tickets, users, organizations, groups, macros, views, search. 18 tools covering the most common agent workflows. Basic-auth with email+API token.
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → Zendesk Support、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Zendesk Support + Gemini
Drive Zendesk Support (the help-desk product) from any AI agent: tickets, users, organizations, groups, macros, views, search. 18 tools covering the most common agent workflows. Basic-auth with email+API token.
前提条件
完整的设置说明已内置在连接器中 (在 store 中选择连接器时可见)。所需环境变量:
ZENDESK_SUBDOMAIN, ZENDESK_EMAIL, ZENDESK_API_TOKEN
步骤 1 — 获取凭证
Setup:
- Sign in to Zendesk as an admin → Admin Center → Apps and integrations → APIs → Zendesk API → Settings → Token access ON.
- Add API token, label it (e.g. 'AnythingMCP'), copy the generated token. It's shown ONCE.
- Set:
ZENDESK_SUBDOMAIN= your account subdomain (e.g.acmeif your URL isacme.zendesk.com)ZENDESK_EMAIL= the agent email of an admin user (the requests will be attributed to this user)ZENDESK_API_TOKEN= the token from step 2
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
步骤 3 — 在 Gemini 中添加连接器
Gemini CLI 从 ~/.gemini/settings.json (Windows: %APPDATA%\gemini\settings.json) 读取 MCP 服务器。添加:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- 从 AnythingMCP 获取你的 MCP API key。
- 保存文件并重启
gemini。 - 在 Gemini CLI 中运行
/mcp—Zendesk Support应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp传入请求的tools数组,使用相同的 Bearer 头。
可用工具
| Tool | What it does |
|---|---|
zendesk_get_current_user | Return the agent user that the API credentials belong to (whoami) |
zendesk_search | Universal search using Zendesk's Lucene-like query syntax |
zendesk_list_tickets | List tickets (cursor-paginated, newest first) |
zendesk_get_ticket | Fetch a single ticket by ID with all fields including custom_fields, tags, requester_id, assignee_id, group_id, status, priority, satisfacti |
zendesk_create_ticket | Create a new ticket |
zendesk_update_ticket | Update a ticket |
zendesk_delete_ticket | Hard-delete a ticket (subject to GDPR retention policy) |
zendesk_list_ticket_comments | List all comments (public replies and internal notes) on a ticket, ordered by creation time |
zendesk_list_users | List users (end-users, agents, admins) |
zendesk_get_user | Fetch a single user by ID |
zendesk_create_or_update_user | Upsert a user by email (matches existing if email already in system) |
zendesk_list_organizations | List organizations |
zendesk_create_organization | Create a new organization |
zendesk_list_groups | List agent groups (used for ticket assignment routing) |
zendesk_list_views | List views — Zendesk's saved filter+sort definitions for tickets |
zendesk_execute_view | Run a view and return the tickets it currently matches |
zendesk_list_ticket_fields | List all ticket fields including custom ones with their IDs, types and allowed values |
zendesk_list_macros | List macros (saved sets of ticket updates an agent can apply with one click — e |
FAQ
Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带 Bearer 头的 MCP httpUrl 连接器。
下一步
这份指南对您有帮助吗?