DMTicket MCP Server
Provides AI agents live access to a DMTicket workspace for managing contacts, conversations, messages, tags, broadcasts, sequences, flows, triggers, and webhooks, enabling reading, segmenting, messaging, and automating tasks.
README
DMTicket MCP Server
Model Context Protocol server for DMTicket — the omnichannel customer-messaging & CRM platform (Zalo, Facebook, Telegram, groups & communities).
It gives AI agents (Claude, Cursor, ChatGPT, custom agents…) live access to a DMTicket workspace: contacts, conversations, messages, tags, custom fields, broadcasts, sequences, flows, triggers and webhooks — so an agent can read, segment, message and automate on your behalf.
How it works
On startup the server fetches ${DMTICKET_API_URL}/api/public-spec.json (the DMTicket OpenAPI spec) and auto-generates one MCP tool per API operation. When DMTicket adds a new endpoint, it becomes an MCP tool on the next restart — no code changes needed.
1. Get your DMTicket API token
- Sign in to your DMTicket workspace at https://dmticket.com
- Go to Settings → Integrations → Workspace Token
- Click Generate (or Regenerate) and Copy the token — it looks like
wsId.xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
The token is scoped to that one workspace and grants access to its public API. Keep it secret; regenerate any time to revoke.
API base URL:
https://dmticket.com/api· Auth header:Authorization: Bearer <token>Quick test:curl https://dmticket.com/api/v1/contacts -H "Authorization: Bearer <token>"
2. Install
git clone https://github.com/doanhnd9989/dmticket-mcp.git
cd dmticket-mcp
npm install
npm run build # outputs dist/
3. Configure your agent
Set two environment variables:
| Variable | Required | Default | Description |
|---|---|---|---|
DMTICKET_API_KEY |
✅ | — | Your workspace token from step 1 |
DMTICKET_API_URL |
— | https://dmticket.com |
Your DMTicket origin |
DMTICKET_MCP_TRANSPORT |
— | both |
stdio, sse, or both |
Claude Code / Claude Desktop
claude mcp add dmticket \
-e DMTICKET_API_KEY=<your-workspace-token> \
-e DMTICKET_API_URL=https://dmticket.com \
-- node /absolute/path/to/dmticket-mcp/dist/index.mjs
Or in claude_desktop_config.json / .mcp.json:
{
"mcpServers": {
"dmticket": {
"command": "node",
"args": ["/absolute/path/to/dmticket-mcp/dist/index.mjs"],
"env": {
"DMTICKET_API_KEY": "<your-workspace-token>",
"DMTICKET_API_URL": "https://dmticket.com"
}
}
}
}
Cursor (.cursor/mcp.json)
{
"mcpServers": {
"dmticket": {
"command": "node",
"args": ["/absolute/path/to/dmticket-mcp/dist/index.mjs"],
"env": { "DMTICKET_API_KEY": "<your-workspace-token>" }
}
}
}
Remote (SSE) mode
DMTICKET_API_KEY=<token> DMTICKET_MCP_TRANSPORT=sse DMTICKET_MCP_PORT=3333 node dist/index.mjs
# then point your agent at http://<host>:3333/sse
Tools
Tool names are the OpenAPI operationId in snake_case — e.g. list_contacts, create_contact, add_contact_tag, list_conversations, send_contact_message, list_broadcasts, create_broadcast, list_flows, list_tags, create_webhook, … The full set is generated live from the spec, so it always matches your DMTicket version.
Security
- The token is a per-workspace credential — treat it like a password. Do not commit it.
- The server only talks to your configured
DMTICKET_API_URL. - Revoke by regenerating the workspace token in DMTicket settings.
License
ISC. This is the MCP integration for DMTicket (https://dmticket.com).
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。