Slack Notifier MCP Server
An MCP server that connects to Slack via Socket Mode (WebSocket) and surfaces real-time message notifications through MCP tools. No public URL or ngrok needed.
README
Slack Notifier MCP Server
An MCP server that connects to Slack via Socket Mode (WebSocket) and surfaces real-time message notifications through MCP tools. No public URL or ngrok needed.
How It Works
This server runs two things simultaneously in a single process:
- Slack Socket Mode client — connects outbound to Slack over WebSocket and receives events in real time
- MCP server (stdio) — exposes tools to query, filter, and manage those notifications
When someone posts a message in Slack, the Socket Mode connection pushes the event to your server. The server stores it in memory (with optional disk persistence), and you can query it via the MCP tools.
Setup
1. Create a Slack App
- Go to api.slack.com/apps and click Create New App → From scratch
- Name it something like "Message Notifier" and pick your workspace
2. Enable Socket Mode
- Go to Settings → Socket Mode and toggle it On
- You'll be prompted to create an App-Level Token — name it something like "socket-mode-token"
- Give it the
connections:writescope - Copy the token (starts with
xapp-) — this is yourSLACK_APP_TOKEN
3. Subscribe to Events
- Go to Features → Event Subscriptions and toggle it On
- Under Subscribe to bot events, add:
message.channels— messages in public channelsmessage.groups— messages in private channelsmessage.im— direct messagesmessage.mpim— group direct messages
- Save changes
4. Add Bot Token Scopes
- Go to Features → OAuth & Permissions
- Under Bot Token Scopes, add:
channels:history— read messages in public channelsgroups:history— read messages in private channelsim:history— read direct messagesmpim:history— read group DMs
- Install (or reinstall) the app to your workspace
5. Invite the Bot
Invite your bot to the channels you want to monitor:
/invite @Message Notifier
6. Configure the MCP Server
Add this to your Claude Desktop / Claude Code MCP config:
{
"mcpServers": {
"slack-notifier": {
"command": "node",
"args": ["/path/to/slack-notifier-mcp-server/dist/index.js"],
"env": {
"SLACK_APP_TOKEN": "xapp-1-your-token-here",
"PERSIST_PATH": "/path/to/notifications.json"
}
}
}
}
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
SLACK_APP_TOKEN |
Yes | — | App-level token (xapp-...) with connections:write scope |
PERSIST_PATH |
No | — | File path to persist notifications across restarts |
Available MCP Tools
slack_get_notifications
Retrieve stored message notifications with filtering:
- Filter by channel, read status, time range
- Pagination support
- Returns newest messages first
slack_mark_notifications_read
Mark notifications as read:
- By specific IDs
- All at once (optionally per-channel)
slack_notification_stats
Get a summary of notification counts grouped by channel — total and unread per channel.
slack_clear_notifications
Permanently delete all stored notifications (requires confirmation).
Building
npm install
npm run build
Running
SLACK_APP_TOKEN=xapp-1-... npm start
The server will connect to Slack via Socket Mode and start the MCP stdio server simultaneously.
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。