What is Slack Mcp Host

slack-mcp-host is a Slack bot application that integrates Machine Control Protocol (MCP) servers with Slack, enabling users to interact with these servers through LLM-powered conversations in dedicated channels.

Use cases

Use cases for slack-mcp-host include automating data queries from MCP servers, facilitating team discussions around data insights, executing commands on MCP servers directly from Slack, and maintaining a history of conversations for future reference.

How to use

To use slack-mcp-host, clone the repository, set up a virtual environment, install dependencies, configure environment variables with your Slack and OpenAI credentials, create a Slack app, and deploy it using Cloudflare Workers.

Key features

Key features include LLM-powered conversations, integration with multiple MCP servers, Markdown rendering support, collapsible tool execution results, conversation history maintenance, and secure configuration management.

Where to use

slack-mcp-host can be used in various fields such as software development, data analysis, and any environment where interaction with MCP servers is required, especially in collaborative settings like Slack workspaces.

Slack MCP Host

A Slack bot that integrates MCP (Machine Control Protocol) servers with Slack, providing LLM-powered interactions in dedicated channels. The bot can execute tools from configured MCP servers and present results in a user-friendly format.

Features

• 🤖 LLM-powered conversations in Slack
• 🔧 Integration with multiple MCP servers
• 📝 Markdown rendering support
• 🔍 Collapsible tool execution results
• 💾 Conversation history maintenance
• 🔐 Secure configuration management

Prerequisites

• Python 3.11+
• uv for dependency management
• A Slack workspace with admin access
• OpenAI API access
• One or more MCP servers

Setup

1. Clone the repository

git clone https://github.com/yourusername/slack-mcp-host.git
cd slack-mcp-host

2. Create and activate virtual environment

uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

3. Install dependencies

uv sync

4. Configure environment

cp .env.example .env

Edit .env with your credentials:

SLACK_API_KEY=xoxb-your-slack-bot-token
OPENAI_API_KEY=your-openai-api-key
OPENAI_BASE_URL=https://api.openai.com/v1
OPENAI_MODEL=gpt-4

# MCP Servers
SLACK_MCP_NEO4J_MOVIES=uvx mcp-neo4j-cypher --url neo4j+s://demo.neo4jlabs.com --username movies --password movies
SLACK_MCP_TIME=uvx mcp-server-time

5. Create Slack App

• Go to api.slack.com/apps
• Click “Create New App” → “From an app manifest”
• Select your workspace
• Copy and paste the contents of manifest.yml
• Create the app and install it to your workspace

Deployment

Cloudflare Workers

1. Install Wrangler

npm install -g wrangler

2. Login to Cloudflare

wrangler login

3. Set secrets

wrangler secret put SLACK_API_KEY
wrangler secret put OPENAI_API_KEY

4. Deploy

wrangler deploy

5. Update Slack App configuration

• Go to your Slack App settings
• Update the Event Subscription URL to your Cloudflare Workers URL:
  https://slack-mcp-host.<your-worker-subdomain>.workers.dev/slack/events

Usage Example

Here’s an example interaction flow:

1. User starts conversation

User: Can you help me find movies directed by Christopher Nolan?

2. Bot responds with tool execution

Bot: I'll help you find movies directed by Christopher Nolan using the Neo4j Movies database.

<details><summary>Tool Results</summary>
Tool neo4j_movies result:
- Inception (2010)
- The Dark Knight (2008)
- Interstellar (2014)
- Memento (2000)
- The Prestige (2006)
</details>

Would you like to know more details about any of these movies?

3. User follows up

User: Tell me more about Inception

4. Bot executes another query

Bot: I'll get the details about Inception for you.

<details><summary>Tool Results</summary>
Tool neo4j_movies result:
Title: Inception (2010)
Director: Christopher Nolan
Cast: Leonardo DiCaprio, Joseph Gordon-Levitt, Ellen Page
Plot: A thief who steals corporate secrets through dream-sharing technology is given the inverse task of planting an idea into the mind of a C.E.O.
</details>

The movie received critical acclaim for its innovative storytelling and visual effects. Would you like to know about any other movies or specific aspects of Inception?

Development

To run locally for development:

uvicorn src.api:app --reload --port 8000

Use ngrok or similar to expose your local server:

ngrok http 8000

Update your Slack App’s Event Subscription URL with the ngrok URL.

Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.