Klavis AI

What is Klavis AI about?

Klavis AI delivers a catalog of Model Context Protocol (MCP) servers that expose the functionality of popular SaaS platforms (GitHub, Gmail, Google Sheets, Slack, Notion, Salesforce, Postgres, etc.) as AI‑friendly endpoints. Both a managed hosted service and self‑hostable Docker images are available, allowing developers to plug external data and actions directly into LLM‑driven agents.

How to use Klavis AI?

1. Hosted service (quickest) – Sign up for a free API key, install the klavis client (pip install klavis or npm install klavis), and call klavis.mcp_server.create_server_instance("GMAIL", "user123") to obtain a ready‑to‑use server URL.
2. Self‑hosting – Pull a Docker image, e.g., docker run -p 5000:5000 ghcr.io/klavis-ai/github-mcp-server:latest, or build from source under klavis/mcp_servers/<service>.
3. Integrate with LLMs – Retrieve the server's tool definitions in OpenAI function‑calling format and pass them to the model as part of a chat completion request.

Key features of Klavis AI

• 50+ ready‑made integrations covering email, version control, spreadsheets, video platforms, CRM, databases, and more.
• Enterprise‑grade hosted infrastructure with 99.9 % SLA, SOC2/GDPR compliance, and scalable auto‑scaling.
• OAuth‑handled servers that abstract away token management for Google, GitHub, Slack, Salesforce, etc.
• Multi‑language client libraries (Python, TypeScript) for rapid prototyping.
• Docker images for every server and source code for full customization.
• Zero‑config Cursor/Claude Desktop integration via generated JSON snippets.

Use cases of Klavis AI

• AI‑powered assistants that read/write Gmail, create GitHub issues, or update Google Sheets on demand.
• Automated workflow bots that sync data between Slack and Notion, or trigger Salesforce actions from LLM prompts.
• Prototype and production pipelines where developers start with the hosted service and later migrate to self‑hosted servers for compliance.
• Function‑calling demonstrations for teaching LLM tool usage with real‑world SaaS APIs.

FAQ from the Klavis AI

Q: Do I need to manage OAuth credentials myself? A: Not when using the hosted service – the platform handles the OAuth flow. For self‑hosted servers, set the required env vars (e.g., KLAVIS_API_KEY) and follow each server’s README.

Q: Is there a free tier? A: Yes, a free API key provides limited monthly usage for the hosted MCP service; additional usage is pay‑as‑you‑go.

Q: Can I add my own MCP server? A: Absolutely. Fork the repository, implement the MCP spec for your service, and publish a Docker image or contribute back.

Q: What languages are supported? A: The client SDK is available for Python and TypeScript/JavaScript. Server implementations exist in Go, Python, and Node.js.

Q: How do I retrieve tool definitions for OpenAI? A: Call klavis.mcp_server.list_tools(server_url, format="OPENAI") to get a JSON schema compatible with OpenAI’s function‑calling feature.

🚀 Quick Start - Run Any MCP Server in 30 Seconds

🌐 Using Hosted Service (Recommended for Production)

Get instant access to 50+ MCP servers with our managed infrastructure - no setup required:

🔗 Get Free API Key →

pip install klavis
# or
npm install klavis

from klavis import Klavis

klavis = Klavis(api_key="your-free-key")
server = klavis.mcp_server.create_server_instance("GMAIL", "user123")

🐳 Using Docker (For Self-Hosting)

# Run GitHub MCP Server
docker run -p 5000:5000 ghcr.io/klavis-ai/github-mcp-server:latest

# Run Gmail MCP Server with OAuth
docker run -it -e KLAVIS_API_KEY=your_key \
  ghcr.io/klavis-ai/gmail-mcp-server-oauth:latest

# Run YouTube MCP Server
docker run -p 5000:5000 ghcr.io/klavis-ai/youtube-mcp-server:latest

🖥️ Cursor Configuration

For Cursor, use our hosted service URLs directly - no Docker setup needed:

{
  "mcpServers": {
    "klavis-gmail": {
      "url": "https://gmail-mcp-server.klavis.ai/mcp/?instance_id=your-instance"
    },
    "klavis-github": {
      "url": "https://github-mcp-server.klavis.ai/mcp/?instance_id=your-instance"
    }
  }
}

💡 Get your personalized configuration instantly:

1. 🔗 Visit our MCP Servers page →
2. Select any service (Gmail, GitHub, Slack, etc.)
3. Copy the generated configuration for your tool
4. Paste into Claude Desktop config - done!

✨ Enterprise-Grade MCP Infrastructure

• 🌐 Hosted Service: Production-ready managed infrastructure with 99.9% uptime SLA
• 🔐 Enterprise OAuth: Seamless authentication for Google, GitHub, Slack, Salesforce, etc.
• 🛠️ 50+ Integrations: CRM, productivity tools, databases, social media, and more
• 🚀 Instant Deployment: Zero-config setup for Claude Desktop, VS Code, Cursor
• 🏢 Enterprise Ready: SOC2 compliant, GDPR ready, with dedicated support
• 📖 Open Source: Full source code available for customization and self-hosting

🎯 Self Hosting Instructions

1. 🐳 Docker Images (Fastest Way to Start)

Perfect for trying out MCP servers or integrating with AI tools like Claude Desktop.

Available Images:

• ghcr.io/klavis-ai/{server-name}-mcp-server:latest - Basic server
• ghcr.io/klavis-ai/{server-name}-mcp-server-oauth:latest - With OAuth support

🔍 Browse All Docker Images →

# Example: GitHub MCP Server
docker run -p 5000:5000 ghcr.io/klavis-ai/github-mcp-server:latest

# Example: Gmail with OAuth (requires API key)
docker run -it -e KLAVIS_API_KEY=your_key \
  ghcr.io/klavis-ai/gmail-mcp-server-oauth:latest

🔗 Get Free API Key →

2. 🏗️ Build from Source

Clone and run any MCP server locally (with or without Docker):

git clone https://github.com/klavis-ai/klavis.git
cd klavis/mcp_servers/github

# Option A: Using Docker
docker build -t github-mcp .
docker run -p 5000:5000 github-mcp

# Option B: Run directly (Go example)
go mod download
go run server.go

# Option C: Python servers  
cd ../youtube
pip install -r requirements.txt
python server.py

# Option D: Node.js servers
cd ../slack  
npm install
npm start

Each server includes detailed setup instructions in its individual README.

Use our managed infrastructure - no Docker required:

pip install klavis  # or npm install klavis

🛠️ Available MCP Servers

Service	Docker Image	OAuth Required	Description
GitHub	ghcr.io/klavis-ai/github-mcp-server	✅	Repository management, issues, PRs
Gmail	ghcr.io/klavis-ai/gmail-mcp-server-oauth	✅	Email reading, sending, management
Google Sheets	ghcr.io/klavis-ai/google_sheets-mcp-server-oauth	✅	Spreadsheet operations
YouTube	ghcr.io/klavis-ai/youtube-mcp-server	❌	Video information, search
Slack	ghcr.io/klavis-ai/slack-mcp-server-oauth	✅	Channel management, messaging
Notion	ghcr.io/klavis-ai/notion-mcp-server-oauth	✅	Database and page operations
Salesforce	ghcr.io/klavis-ai/salesforce-mcp-server-oauth	✅	CRM data management
Postgres	ghcr.io/klavis-ai/postgres-mcp-server	❌	Database operations
...	...	...	...

And more! 🔍 View All 50+ Servers → | 🐳 Browse Docker Images →

💡 Usage Examples

For existing MCP implementations:

Python

from klavis import Klavis

klavis = Klavis(api_key="your-key")
server = klavis.mcp_server.create_server_instance(
    server_name="YOUTUBE",
    user_id="user123",
    platform_name="MyApp"
)

TypeScript

import { KlavisClient } from 'klavis';

const klavis = new KlavisClient({ apiKey: 'your-key' });
const server = await klavis.mcpServer.createServerInstance({
    serverName: "Gmail",
    userId: "user123"
});

With AI Frameworks

OpenAI Function Calling

from openai import OpenAI
from klavis import Klavis

klavis = Klavis(api_key="your-key")
openai = OpenAI(api_key="your-openai-key")

# Create server and get tools
server = klavis.mcp_server.create_server_instance("YOUTUBE", "user123")
tools = klavis.mcp_server.list_tools(server.server_url, format="OPENAI")

# Use with OpenAI
response = openai.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Summarize this video: https://..."}],
    tools=tools.tools
)

📖 View Complete Examples →

🌐 Hosted MCP Service - Zero Setup Required

Perfect for individuals and businesses who want instant access without infrastructure complexity:

✨ Why Choose Our Hosted Service:

• 🚀 Instant Setup: Get any MCP server running in 30 seconds
• 🔐 OAuth Handled: No complex authentication setup required
• 🏗️ No Infrastructure: Everything runs on our secure, scalable cloud
• 📈 Auto-Scaling: From prototype to production seamlessly
• 🔄 Always Updated: Latest MCP server versions automatically
• 💰 Cost-Effective: Pay only for what you use, free tier available

💻 Quick Integration:

from klavis import Klavis

# Get started with just an API key
klavis = Klavis(api_key="your-free-key")

# Create any MCP server instantly
gmail_server = klavis.mcp_server.create_server_instance(
    server_name="GMAIL",
    user_id="your-user-id", 
    platform_name="MyApp"
)

# Server is ready to use immediately
print(f"Gmail MCP server ready: {gmail_server.server_url}")

🔗 Get Free API Key → | 📖 Complete Documentation →

🔐 OAuth Authentication (For OAuth-Enabled Servers)

Some servers require OAuth authentication (Google, GitHub, Slack, etc.). OAuth implementation requires significant setup and code complexity:

# Run with OAuth support (requires free API key)
docker run -it -e KLAVIS_API_KEY=your_free_key \
  ghcr.io/klavis-ai/gmail-mcp-server-oauth:latest

# Follow the displayed URL to authenticate
# Server starts automatically after authentication

Why OAuth needs additional implementation?

• 🔧 Complex Setup: Each service requires creating OAuth apps with specific redirect URLs, scopes, and credentials
• 📝 Implementation Overhead: OAuth 2.0 flow requires callback handling, token refresh, and secure storage
• 🔑 Credential Management: Managing multiple OAuth app secrets across different services
• 🔄 Token Lifecycle: Handling token expiration, refresh, and error cases

Our OAuth wrapper simplifies this by handling all the complex OAuth implementation details, so you can focus on using the MCP servers directly.

Alternative: For advanced users, you can implement OAuth yourself by creating apps with each service provider. Check individual server READMEs for technical details.

📚 Resources & Community

Resource	Link	Description
📖 Documentation	docs.klavis.ai	Complete guides and API reference
💬 Discord	Join Community	Get help and connect with users
🐛 Issues	GitHub Issues	Report bugs and request features
📦 Examples	examples/	Working examples with popular AI frameworks
🔧 Server Guides	mcp_servers/	Individual server documentation

🤝 Contributing

We love contributions! Whether you want to:

• 🐛 Report bugs or request features
• 📝 Improve documentation
• 🔧 Build new MCP servers
• 🎨 Enhance existing servers

Check out our Contributing Guide to get started!

📜 License

MIT License - see LICENSE for details.

---