Klavis
Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
What is Klavis?
Klavis is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to klavis ai: mcp integration platforms that let ai agents use tools reliably at any scale
Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Klavis AI: MCP integration platforms that let AI agents use
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx klavisConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Klavis
Klavis AI is a managed MCP integration platform that provides hosted MCP servers for over 40 popular services — including Gmail, GitHub, Slack, Google Sheets, Notion, YouTube, Salesforce, and Postgres — allowing AI agents to use these tools reliably at any scale without self-hosting infrastructure. It offers Python and TypeScript SDKs for programmatic server instantiation, a REST API, OAuth support for user-level authentication, and a Strata feature that combines multiple MCP servers into an optimised single context window. Developers and AI teams use Klavis when they want production-ready tool integrations for their agents without managing individual MCP server deployments.
Prerequisites
- A Klavis AI account and KLAVIS_API_KEY from https://klavis.ai
- Python 3.8+ (for Python SDK) or Node.js 18+ (for TypeScript SDK)
- Docker (optional, for self-hosting individual MCP servers)
- An MCP-compatible AI client (Claude Desktop, Claude Code, or a custom agent using the Klavis SDK)
Get a Klavis API key
Sign up at klavis.ai and obtain your KLAVIS_API_KEY from the dashboard. This key authenticates all SDK and REST API calls.
export KLAVIS_API_KEY=your-klavis-api-key-hereInstall the SDK
Install the Klavis client library for your preferred language.
# Python
pip install klavis
# Node.js / TypeScript
npm install klavisCreate an MCP server instance via SDK
Use the SDK to spin up a hosted MCP server instance for a specific integration. Each user or session gets its own instance.
# Python
from klavis import Klavis
klavis = Klavis(api_key="your-klavis-api-key")
server = klavis.mcp_server.create_server_instance("GMAIL", "user-123")
print(server.server_url) # SSE endpoint for this instance
# TypeScript
import { KlavisClient } from 'klavis';
const klavis = new KlavisClient({ apiKey: 'your-klavis-api-key' });
const server = await klavis.mcpServer.createServerInstance({
serverName: 'Gmail',
userId: 'user-123'
});Configure Claude Desktop with a hosted Klavis endpoint
Add the SSE URL returned by the SDK to your Claude Desktop config so Claude can access the tools.
{
"mcpServers": {
"klavis-gmail": {
"url": "https://gmail-mcp-server.klavis.ai/mcp/?instance_id=your-instance-id"
},
"klavis-github": {
"url": "https://github-mcp-server.klavis.ai/mcp/?instance_id=your-instance-id"
}
}
}Self-host a specific MCP server with Docker (optional)
For compliance or latency requirements, run an individual Klavis MCP server locally using Docker.
# GitHub MCP Server
docker pull ghcr.io/klavis-ai/github-mcp-server:latest
docker run -p 5000:5000 \
-e KLAVIS_API_KEY=$KLAVIS_API_KEY \
ghcr.io/klavis-ai/github-mcp-server:latest
# Gmail MCP Server (with OAuth)
docker pull ghcr.io/klavis-ai/gmail-mcp-server:latest
docker run -it -p 5001:5000 \
-e KLAVIS_API_KEY=$KLAVIS_API_KEY \
ghcr.io/klavis-ai/gmail-mcp-server:latestKlavis Examples
Client configuration
Claude Desktop config connecting to hosted Klavis MCP servers via SSE transport.
{
"mcpServers": {
"klavis-gmail": {
"url": "https://gmail-mcp-server.klavis.ai/mcp/?instance_id=your-instance-id"
},
"klavis-github": {
"url": "https://github-mcp-server.klavis.ai/mcp/?instance_id=your-instance-id"
},
"klavis-slack": {
"url": "https://slack-mcp-server.klavis.ai/mcp/?instance_id=your-instance-id"
}
}
}Prompts to try
With Klavis MCP servers connected, Claude can interact with your real accounts and services.
- "Search my Gmail for unread emails from last week and summarise them"
- "Create a new GitHub issue in my repo titled 'Fix login timeout bug' with a description"
- "Post a message to the #engineering Slack channel saying the deploy is done"
- "Look up the latest commits in my GitHub repo and write a changelog entry"Troubleshooting Klavis
create_server_instance returns 401 Unauthorized
Verify your KLAVIS_API_KEY is correct and has not expired. Log in to klavis.ai and check your API key under account settings. Re-export the key: `export KLAVIS_API_KEY=your-key`.
Gmail or OAuth-based integrations fail to authenticate
Klavis handles OAuth for supported services. During the first connection, you will be redirected to complete the OAuth flow in your browser. Ensure the redirect URI in your OAuth app settings matches the Klavis callback URL provided in their documentation.
Self-hosted Docker container cannot connect to Klavis services
Ensure the KLAVIS_API_KEY environment variable is passed to the Docker container via `-e KLAVIS_API_KEY=$KLAVIS_API_KEY`. Also confirm the container has outbound internet access to reach klavis.ai.
Frequently Asked Questions about Klavis
What is Klavis?
Klavis is a Model Context Protocol (MCP) server that klavis ai: mcp integration platforms that let ai agents use tools reliably at any scale It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Klavis?
Follow the installation instructions on the Klavis GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Klavis?
Klavis works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Klavis free to use?
Yes, Klavis is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Klavis Alternatives — Similar Developer Tools Servers
Looking for alternatives to Klavis? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Klavis in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Klavis?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.