SeaTalk MCP Server
Enables sending and reading SeaTalk messages, including DMs, group chats, and message history, plus employee lookup via the SeaTalk Open Platform API.
README
SeaTalk MCP Server
An MCP server that connects to the SeaTalk Open Platform API, giving you 8 tools:
| Tool | What it does |
|---|---|
send_direct_message |
Send a DM to a SeaTalk user via the bot |
send_group_message |
Send a message to a group chat |
list_groups |
List all groups the bot has joined |
get_group_info |
Get details about a specific group |
get_group_history |
Read recent messages in a group (up to 7 days) |
find_employee_by_email |
Look up employee codes by email |
get_message |
Retrieve a specific message by ID |
get_thread_messages |
Read messages in a thread |
Prerequisites
- Node.js 18+ — Download from nodejs.org (pick LTS)
- SeaTalk App credentials — From open.seatalk.io:
- Create an App/Bot
- Copy your App ID and App Secret
- Enable messaging and contacts capabilities
Quick Start (Local)
# Install dependencies
npm install
# Build the TypeScript code
npm run build
# Set your credentials and run
SEATALK_APP_ID=your_id SEATALK_APP_SECRET=your_secret npm start
The server starts on http://localhost:3000/sse.
Deploy to Railway (Recommended for Non-Devs)
- Go to railway.app and sign up (free tier available)
- Click "New Project" → "Deploy from GitHub repo"
- Connect your GitHub and upload this code (or use "Deploy from local")
- Go to Variables tab and add:
SEATALK_APP_ID= your App IDSEATALK_APP_SECRET= your App SecretPORT= 3000
- Railway will auto-detect the Dockerfile and deploy
- Copy the public URL Railway gives you (e.g.,
your-app.up.railway.app) - Your MCP endpoint is:
https://your-app.up.railway.app/sse
Deploy to Render
- Go to render.com and sign up
- Click "New" → "Web Service"
- Connect your repo or upload code
- Set Build Command:
npm install && npm run build - Set Start Command:
npm start - Add Environment Variables:
SEATALK_APP_ID= your App IDSEATALK_APP_SECRET= your App Secret
- Deploy and copy the URL
Connect to Migoo
Once deployed, add it as a custom MCP:
- Use the URL:
https://YOUR-DEPLOYED-URL/sse - That's it — the tools will appear automatically
Project Structure
seatalk-mcp-server/
├── src/
│ └── index.ts ← Main server code (all tools + API client)
├── package.json ← Dependencies
├── tsconfig.json ← TypeScript config
├── Dockerfile ← For Docker-based deploys
├── Procfile ← For Railway/Heroku
├── .env.example ← Template for env vars
└── README.md ← This file
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。