Klavis-AI

Klavis AI

Community Klavis-AI
Updated

Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale

Klavis AI

๐Ÿ“ฆ MCP integration layers that let AI agents use tools reliably at any scale

DocumentationWebsiteDiscordLicense: MIT

๐ŸŽฏ Choose Your Solution

๐Ÿ“ฆ Strata

Unified MCP Router

One MCP server for AI agents to use tools reliably at any scale

๐Ÿ› ๏ธ MCP Integrations

50+ Production MCP Servers

Self-hosted or managed MCP servers with enterprise OAuth support for all major services

Strata

Strata is one MCP server that guides your AI agents use tools reliably progressively at any scale.

Why Strata?

๐ŸŽฏ Scalable Tool Integration โ†’ Beyond 40-50 tool limits ๐Ÿš€ Progressive Discovery โ†’ Guides agents from intent to action, step-by-step.

๐Ÿ“– Learn More โ†’

MCP Integrations

50+ production MCP servers. OAuth included. Deploy anywhere.

Connect your AI to GitHub, Gmail, Slack, Salesforce, and more - all with enterprise OAuth and Docker support.

๐Ÿ” Real OAuth โ†’ Not just API keys ๐Ÿณ Docker ready โ†’ One-line deploy

๐ŸŒ Browse All Servers โ†’

๐Ÿš€ Quick Start

Option 1: Open Source

Self-host everything on your own infrastructure:

# Run any MCP Integration
docker pull ghcr.io/klavis-ai/github-mcp-server:latest
docker run -p 5000:5000 ghcr.io/klavis-ai/github-mcp-server:latest

# Install Open Source Strata locally
pipx install strata-mcp
strata add --type stdio playwright npx @playwright/mcp@latest

Option 2: Use Hosted Service by WebUI

Get instant access without any setup:

  1. Sign Up: Create account โ†’
  2. Get Started: Follow quickstart guide โ†’
  3. Use Strata or individual MCP servers in Claude Code, Cursor, VSCode, etc.

Ready in under 2 minutes! ๐Ÿš€

Option 3: SDK

Build custom applications with our SDKs:

# Python SDK
from klavis import Klavis
from klavis.types import McpServerName

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

# Create Strata instance
strata = klavis.mcp_server.create_strata_server(
    user_id="user123",
    servers=[McpServerName.GMAIL, McpServerName.YOUTUBE],
)

# Or use individual MCP servers
gmail = klavis.mcp_server.create_server_instance(
    server_name=McpServerName.GMAIL,
    user_id="user123",
)
// TypeScript SDK
import { KlavisClient, McpServerName } from 'klavis';

const klavis = new KlavisClient({ apiKey: 'your-api-key' });

// Create Strata instance
const strata = await klavis.mcpServer.createStrataServer({
    userId: "user123",
    servers: [McpServerName.GMAIL, McpServerName.YOUTUBE]
});

// Or use individual MCP servers
const gmail = await klavis.mcpServer.createServerInstance({
    serverName: McpServerName.GMAIL,
    userId: "user123"
});

Option 4: Direct API

Use REST API for any programming language:

# Create Strata server
curl -X POST "https://api.klavis.ai/v1/mcp-server/strata" \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "user_id": "user123",
    "servers": ["GMAIL", "YOUTUBE"]
  }'

# Create individual MCP server
curl -X POST "https://api.klavis.ai/v1/mcp-server/instance" \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "server_name": "GMAIL",
    "user_id": "user123"
  }'

๐Ÿ“– Complete Documentation โ†’

๐Ÿ“š Resources

๐Ÿ“œ License

  • Root Repository: Apache 2.0 license - see LICENSE

Klavis AI (YC X25) ๐Ÿš€ Empowering AI with Seamless Integration

MCP Server ยท Populars

MCP Server ยท New

    1ch1n

    MyChatArchive

    Local-first AI memory archive. Import ChatGPT, Claude, and Grok exports, generate semantic embeddings, and search via MCP server. Zero cloud, zero cost.

    Community 1ch1n
    butterbase-ai

    butterbase

    Open-source backend-as-a-service. Postgres, auth, storage, functions, AI gateway, MCP.

    Community butterbase-ai
    GoPlusSecurity

    GoPlus AgentGuard

    Security guard for AI agents โ€” blocks malicious skills, prevents data leaks, protects secrets. 24 detection rules, runtime action evaluation, trust registry.

    Community GoPlusSecurity
    respawn-llc

    tool-filter-mcp

    MCP proxy server that filters tools from upstream MCP servers via regex-based deny list

    Community respawn-llc
    Kaelio

    ktx-ai-data-agents-context

    ktx is an executable context layer for data and analytics agents ๐Ÿ™ Allow Claude Code, Codex, and any AI agent to query data accurately through MCP with skills, memory and a semantic layer

    Community Kaelio