摘要
Zammad 开源服务台：工单、其文章、用户、组织和群组，以及对整个工单库的全文搜索。运行在您自己的 Zammad 实例上的 REST API v1，token 认证。
引导式设置
2 分钟将 Zammad 连接到 Gemini
开始 AnythingMCP Cloud 免费试用，在引导式设置中连接 Zammad，再把你的 MCP URL 添加到 Gemini。无需代码，也无需自行运行服务器。
无需信用卡 · 7 天试用 · 提供自托管方案
试试这样问
Zammad 的示例提示
点击任意提示即可复制，然后粘贴到 Claude、ChatGPT、Cursor、Gemini、Copilot 或 OpenClaw 中，在该连接器上运行。
Claude 是 AI，可能会出错。请核对回答。
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → Zammad、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Zammad + Gemini
Zammad 开源服务台：工单、其文章、用户、组织和群组，以及对整个工单库的全文搜索。运行在您自己的 Zammad 实例上的 REST API v1，token 认证。
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:
ZAMMAD_URL, ZAMMAD_API_TOKEN
步骤 1 — 获取凭证
Getting a token
- Sign in to Zammad, open your avatar → Profile → Token Access, and switch token access on if an admin has not already.
- Create a token with the permissions the agent needs —
ticket.agentto read and answer tickets,adminonly if you really want the agent to change configuration. - Put it in
ZAMMAD_API_TOKENand your instance's base URL (no trailing slash, no/api) inZAMMAD_URL.
The Authorization header is Token token=…, Zammad's own scheme — not Bearer. This adapter sends it correctly; it is the first thing to check when hand-building a Zammad connector that 401s with a token you know is good.
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
步骤 3 — 在 Gemini 中添加连接器
你的服务器 URL： 在 AnythingMCP 中打开 MCP Servers → 此连接器所在的服务器，复制它的 URL（
https://cloud.anythingmcp.com/mcp/…）。本指南中出现YOUR_SERVER_ID的地方都用它替换。
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/YOUR_SERVER_ID",
"headers": { "X-API-Key": "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—Zammad应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID传入请求的tools数组,使用相同的X-API-Key请求头。
可用工具
| Tool | What it does |
|---|---|
zammad_get_me | Read the user the token belongs to, with their roles, group memberships and permissions |
zammad_list_tickets | List tickets, newest first, with state, priority, group, owner and customer |
zammad_search_tickets | Full-text search across tickets |
zammad_get_ticket | Read one ticket by number or id with all its attributes: state, priority, owner, customer, group, SLA and custom fields |
zammad_list_ticket_articles | Read the conversation on one ticket: every article in order, with sender, type, body and whether it is internal |
zammad_list_users | List users (agents and customers) with their name, e-mail, organization and active flag |
zammad_search_users | Find a user by name, e-mail or phone fragment — the usual first step before opening a ticket for somebody |
zammad_list_organizations | List organizations (the customer companies tickets are grouped under) with their domain, note and VIP flag |
zammad_list_groups | List the groups (queues) tickets are routed into, with their assignment and follow-up settings |
zammad_create_ticket | Open a real ticket in the live instance |
zammad_add_article | Add an article to an existing ticket |
FAQ
Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带自定义请求头的 MCP httpUrl 连接器。
下一步
这份指南对你有帮助吗?