Klavis

🚀 Open Source, easy to use MCPs on Slack, Discord and Web

Klavis AI is dedicated to developing open - source and user - friendly MCPs available on Slack, Discord, and the Web. Our offerings empower both non - technical users and developers, making AI workflows accessible and manageable.

• 💬 Slack & Discord & Web Clients: Seamlessly run MCPs directly from your preferred messaging platforms.
• ☁️ Hosted MCP Servers: Gain access to powerful tools without the hassle of infrastructure management.
• 🎛️ Simple Web UI: Configure and manage all aspects without any coding requirements.

🚀 Quick Start

MCP Client Setup

For detailed instructions on setting up MCP clients, refer to the platform - specific documentation:

• - A comprehensive guide for setting up and running the Discord bot.
• - A step - by - step guide for creating a Slack app and establishing the connection.

MCP Server Setup

For detailed instructions on setting up MCP servers, refer to the README file in each server folder:

• : For Discord API integration.
• : Convert between various file formats using Pandoc.
• : For web crawling and data collection.
• : For more in - depth web research tasks.
• : Perform GitHub repository operations.
• : A Markdown conversion tool.
• : For PostgreSQL database operations.
• : Create professional web reports based on user queries.
• : For email services.
• : For Slack API integration.
• : For database operations.
• : Extract and convert YouTube video information.

✨ Features

🎬 Watch Our Demo

Get a glimpse of how effortlessly you can use MCPs (such as our Report Generator, YouTube tools, and Document Converters) directly from Slack or Discord:

Find more case - study videos on our website.

🔧 Technical Details

🏗️ Architecture

Klavis is composed of two main components:

MCP Servers

Located in the mcp_servers/ directory, these service - specific modules offer a range of capabilities:

• Report Generation: Create professional reports from diverse data sources.
• YouTube: Download, analyze, and transform YouTube content.
• Document Conversion: Convert between various file formats using Pandoc.
• GitHub: Perform GitHub repository operations.
• Slack: Integrate with the Slack API.
• Supabase: Conduct database operations.
• Firecrawl: Crawl the web and collect data.
• Resend: Provide email services.
• Postgres: Operate on PostgreSQL databases.
• Discord: Integrate with the Discord API.

MCP Clients

Located in the mcp - clients/ directory, these client applications connect to MCP servers and interact with end - user platforms:

• Discord Bot: An interactive AI assistant for Discord.
• Slack Bot: An interactive AI assistant for Slack.
• Base Client: A module that shares functionality across all platform clients.

🧩 Extending Klavis

Adding a New Tool

1. Create a new directory in mcp_servers/.
2. Implement the MCP server interface.
3. Register your tools with appropriate schemas.
4. Connect to your client via the standard SSE protocol.

Adding a New Client Platform

1. Create a new client module in mcp - clients/.
2. Extend the functionality of base_bot.py.
3. Implement platform - specific message handling.
4. Connect to MCP servers using mcp_client.py.

🤝 Contributing

We welcome contributions! Refer to our Contributing Guidelines for details on submitting changes. Join our Discord community to share ideas and get assistance.

📚 Documentation

📚 Citation

If you use Klavis in your research or project, please cite:

@software{klavis2025,
  author = {Klavis AI},
  title = {Klavis: Open - Source MCPs on Slack, Discord and Web},
  year = {2025},
  publisher = {GitHub},
  url = {https://github.com/klavis-ai/klavis}
}

📄 License

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