Production-ready MCP integrations for AI applications

Introduction

Klavis AI makes it effortless to connect to production-ready MCP servers & clients at scale. Integrate MCPs with your AI applications in a minute, and scale to millions of users using our open-source infrastructure, hosted servers, and multi-platform clients!

✨ Key Features

Klavis AI removes the barrier to using MCPs by providing:

• Production-Ready MCP Servers: All our MCP Servers come from official sources or are internally evaluated by Klavis and our customers.
• Built-In Authentications: Secure authentication out of the box for both developers and end-users.
• MCP Client Integrations: We support MCP Client Integration, allowing you to interact via Klavis Slack, Discord, or web MCP client and integrate into your workflows seamlessly.
• 100+ Tool Integrations & Customizations: Support for various tools and customized MCP servers tailored to your needs.

🚀 Quick Start

To run self hosted versions, check out the detailed readme in each MCP server and MCP client below.

MCP Servers

• Discord: For Discord API integration
• Document Conversion (Pandoc): Convert between various file formats using Pandoc
• Firecrawl: For web crawling and data collection
• Firecrawl Deep Research: For deeper web research tasks
• GitHub: Perform GitHub repository operations
• Markitdown: Markdown conversion tool
• Postgres: For PostgreSQL database operations
• Report Generation: Create professional web reports from user query
• Resend: For email services
• Shopify: For Shopify Admin API integration
• Slack: For Slack API integration
• Supabase: For database operations
• YouTube: Extract and convert YouTube video information
• Jira: manage your sprint
• And More!

MCP Clients

• Discord MCP Client Setup Guide
• Slack MCP Client Setup Guide
• Web Chat MCP Client Setup Guide

Hosted solutions

1. Sign up for Klavis platform and create your API key

2. Create a new MCP server instance

curl --request POST 
  --url https://api.klavis.ai/mcp-server/instance/create 
  --header 'Authorization: Bearer <KLAVIS_API_KEY>' 
  --header 'Content-Type: application/json' 
  --data '{
  "serverName": "<MCP_SERVER_NAME>",
  "userId": "<USER_ID>",
  "platformName": "<PLATFORM_NAME>"
}'

Note: It will return an MCP server URL that takes care of everything for you!

3. Set up auth token or use our in-house OAuth flow (if the MCP Server requests private info)

curl --request POST 
  --url https://api.klavis.ai/mcp-server/instance/set-auth-token 
  --header 'Authorization: Bearer <KLAVIS_API_KEY>' 
  --header 'Content-Type: application/json' 
  --data '{
  "instanceId": "<string>",
  "authToken": "<string>"
}'

Check out our documentation for more details!

🤝 Contributing

We love contributions! Please check our Contributing Guidelines for details on how to submit changes. Join our Discord community to discuss ideas and get help.

📜 License

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