Klavis AI makes it effortless to connect to production-ready MCP servers & clients at scale. Integrate with your AI application in under a minute, and scale to millions of users using our open-source infrastructure, hosted servers, and multi-platform clients!
Klavis AI lowers the barrier to using MCPs by providing:
- Stable Production-Ready MCP Servers: 100% connection guarantee with reliable MCP servers on dedicated infrastructure.
- Built-In Authentication: Secure authentication out of the box with built-in OAuth flows and secrets management for both developers and end-users.
- High-Quality: All our MCP Servers come from official sources or are internally evaluated by Klavis and our customers.
- MCP Client integration: 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 & Customization: Support for various tools and customized MCP servers tailored to your needs.
To run self hosted versions, check out the detailed readme in each MCP server and MCP client below.
- 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
- Slack: For Slack API integration
- Supabase: For database operations
- YouTube: Extract and convert YouTube video information
- Jira: manage your sprint
- And More!
-
Sign up for Klavis platform and create your API key
-
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!
- 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!
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.
This project is licensed under the MIT License - see the LICENSE file for details.