strata
MCP serverDev toolsStrata is a developer tool integration that lets your AI manage large sets of tools by loading them step by step as needed. Once added, your AI can draw on big tool collections without getting overwhelmed, picking up each tool right when a task calls for it.
Use strata in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add strata and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use strata
Needs your own strata account. You sign in to it and approve access when you connect.
Details
Available today. Use it from your connected AI after setup.
After adding Strata, give your AI the tools you want it to handle, and it will load each one only when a task calls for it.
What your AI can do with it
- Load tools step by step as tasks need them
- Manage large sets of tools
- Work with tool collections at any scale
- Use only the tools relevant to the current step
Install strata
The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.
Claude Code
claude mcp add --transport http --scope user strata 'https://strata.klavis.ai/mcp/'Run it once in your project, then open /mcp to approve any sign-in the server asks for.
Claude Desktop
https://strata.klavis.ai/mcp/Add a custom connector in Settings, paste this address, and approve the sign-in.
Cursor
cursor://anysphere.cursor-deeplink/mcp/install?name=strata&config=eyJ1cmwiOiJodHRwczovL3N0cmF0YS5rbGF2aXMuYWkvbWNwLyJ9Open the link and Cursor adds the server at that address.
ChatGPT
https://strata.klavis.ai/mcp/In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.
Codex
codex mcp add strata --url 'https://strata.klavis.ai/mcp/'Run it once, then sign in with codex mcp login strata if the server asks for an account.
From the project's README
As published by klavis-ai/klavis in README.md.
🎯 Choose Your Solution
Quick Start
Option 1: Cloud-hosted - klavis.ai
Option 2: Self-host
# 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 3: SDK
# Python SDK
from klavis import Klavis
from klavis.types import McpServerName
klavis = Klavis(api_key="your-key")
# Create Strata instance
strata = klavis_client.mcp_server.create_strata_server(
user_id="user123",
servers=[McpServerName.GMAIL, McpServerName.SLACK],
)
# 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: [Klavis.McpServerName.Gmail, Klavis.McpServerName.Slack],
});
// Or use individual MCP servers
const gmail = await klavis.mcpServer.createServerInstance({
serverName: McpServerName.GMAIL,
userId: "user123"
});
Option 4: REST API
# 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", "SLACK"]
}'
# 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"
}'
Resources
Signals
- GitHub stars
- 6k
- Forks
- 563
- Last commit
- Jun 2026
Advanced
- Delivery
- strata MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
- Item type
- mcp-server
- Key
ai-klavis-strata- Source
- github.com/klavis-ai/klavis
- Hosted endpoint
https://strata.klavis.ai/mcp/