Slack Webhook
Post messages to Slack channels using incoming webhooks.
Slack Webhook MCP Server
A Model Context Protocol (MCP) server that enables LLM applications like Claude Desktop to send messages to Slack channels via incoming webhooks.
Features
- Send plain text or markdown-formatted messages to Slack
- Simple and secure webhook URL management
- Built with Deno for modern TypeScript development
- Full test coverage
Installation
Prerequisites
- Deno installed on your system
- A Slack workspace with incoming webhooks enabled
- Claude Desktop (or another MCP-compatible client)
Setup
-
Clone this repository:
git clone https://github.com/yourusername/slack-webhook-mcp.git cd slack-webhook-mcp -
Create a Slack incoming webhook:
- Go to your Slack workspace's App Directory
- Search for "Incoming WebHooks" and add it
- Choose a channel and create a webhook URL
- Copy the webhook URL (it should look like
https://hooks.slack.com/services/T00000000/B00000000/XXXXXXXXXXXXXXXXXXXXXXXX)
-
Configure your environment:
cp .env.example .env # Edit .env and add your webhook URL
Configuration
Claude Desktop
Add this server to your Claude Desktop configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"slack-webhook": {
"command": "deno",
"args": ["run", "--allow-net", "--allow-env", "--allow-read", "/path/to/slack-webhook-mcp/src/index.ts"],
"env": {
"SLACK_WEBHOOK_URL": "https://hooks.slack.com/services/YOUR/WEBHOOK/URL"
}
}
}
}
Using Compiled Binary
You can also compile the server to a standalone executable:
deno task build
Then use the binary in your configuration:
{
"mcpServers": {
"slack-webhook": {
"command": "/path/to/slack-webhook-mcp/slack-webhook-server",
"env": {
"SLACK_WEBHOOK_URL": "https://hooks.slack.com/services/YOUR/WEBHOOK/URL"
}
}
}
}
Usage
Once configured, you can use the following tool in Claude Desktop:
send_slack_message
Send a message to your configured Slack channel.
Parameters:
message(required): The message text to sendwebhook_url(optional): Override the default webhook URLformat(optional): Message format - "text" or "markdown" (default: "markdown")
Examples:
- "Send a Slack message saying the deployment was successful"
- "Notify the team on Slack that the tests are passing"
- "Send 'Build failed: timeout in test suite' to Slack with plain text format"
Development
Available Commands
# Run in development mode with auto-reload
deno task dev
# Run tests
deno task test
# Run tests with coverage
deno task test:coverage
# Type checking
deno task check
# Linting
deno task lint
# Format code
deno task fmt
# Build standalone executable
deno task build
Project Structure
slack-webhook-mcp/
├── src/
│ ├── index.ts # Entry point
│ ├── server.ts # MCP server implementation
│ ├── tools/
│ │ ├── slack_webhook.ts # Slack webhook tool
│ │ └── slack_webhook_test.ts # Tool tests
│ ├── types.ts # TypeScript types
│ └── index_test.ts # Integration tests
├── deno.json # Deno configuration
├── README.md # This file
└── .env.example # Environment variables example
Security
- Never commit your
.envfile or webhook URLs to version control - Webhook URLs are validated to ensure they match Slack's format
- All errors are handled gracefully without exposing sensitive information
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Run tests and ensure they pass (
deno task test) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Built using the Model Context Protocol SDK
- Powered by Deno
- Integrates with Slack Incoming Webhooks
関連サーバー
FastIntercom
A high-performance MCP server for analyzing Intercom conversations with fast, local access via caching and background sync.
Tldv
Connect your AI agents to Google-Meet, Zoom & Microsoft Teams through tl;dv
Python LINE MCP Server
An MCP server for accessing and interacting with LINE Bot messages.
DeepL
Translate text using the DeepL API.
Gemini
Integrate with Google's Gemini AI models for various tasks.
Voice Mode
A server for natural voice conversations with AI assistants like Claude and ChatGPT.
MCP Discord Agent Communication
Enables asynchronous communication between AI agents and users through Discord, ideal for long-running tasks.
Mac Messages MCP
A Python bridge for interacting with the macOS Messages app.
Help Scout
An MCP server that enables AI assistants to interact with Help Scout data, such as customers and conversations.
WeCom Bot
Sends various types of messages to a WeCom (WeChat Work) group robot.