Strata

ai.klavisPublished by klavis.aiOfficial publisherv1.0.0Updated Nov 3, 2026

MCP server for progressive tool usage at any scale (see https://klavis.ai)

VerifiedStreamable HTTPWeb executableProductivity & WorkflowAI & ML

Overview

AI-generated overview

Klavis Strata is a hosted MCP layer that bundles many prebuilt integrations behind one endpoint and manages tool context for the agent.

What you can do
  • Combine multiple prebuilt MCP integrations (such as Gmail and Slack) into a single Strata server instance
  • Expose those integrations to an agent through one remote MCP endpoint with OAuth sign-in
  • Keep the agent's context window in check by presenting tools progressively rather than all at once
  • Create and manage Strata instances or individual integration instances through the Klavis Python and TypeScript SDKs or the REST API
  • Optionally self-host the open-source Strata package and attach local stdio MCP servers
When to use it
Useful when an assistant needs several third-party integrations at once and you want one connection instead of many, or when a large tool catalog would otherwise crowd out the context window. Also relevant if you are building agents on Klavis and want to provision integration instances programmatically.
Requirements
A remote endpoint at strata.klavis.ai with OAuth authentication, which is required. The SDK and REST API options need a Klavis API key. Self-hosting needs Python with pipx, or Docker for the individual integration images.
Before you install
The hosted service acts as a broker for connected accounts such as Gmail and Slack, so the agent can read and act on data in those accounts once authorized. OAuth grants and any Klavis API key are sensitive credentials. Self-hosting and SDK usage are separate paths from the hosted endpoint and may involve different terms.

Installation

In SourceWeft

  1. Open Strata in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.klavis%2Fstrata/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "strata": {
      "type": "http",
      "url": "https://strata.klavis.ai/mcp/"
    }
  }
}

README

🎯 Choose Your Solution

Strata

Intelligent connectors for your AI agent, optimize context window

MCP Integrations

100+ prebuilt integrations out-of-the-box, with OAuth support

MCP Sandbox

scalable MCP environments for LLM training and RL

Quick Start

Option 1: Cloud-hosted - klavis.ai

Quickstart guide →

Option 2: Self-host

bash
# Run any MCP Integrationdocker pull ghcr.io/klavis-ai/github-mcp-server:latestdocker run -p 5000:5000 ghcr.io/klavis-ai/github-mcp-server:latest
# Install Open Source Strata locallypipx install strata-mcpstrata add --type stdio playwright npx @playwright/mcp@latest

Option 3: SDK

python
# Python SDKfrom klavis import Klavisfrom klavis.types import McpServerName
klavis = Klavis(api_key="your-key")
# Create Strata instancestrata = klavis_client.mcp_server.create_strata_server(    user_id="user123",    servers=[McpServerName.GMAIL, McpServerName.SLACK],)
# Or use individual MCP serversgmail = klavis.mcp_server.create_server_instance(    server_name=McpServerName.GMAIL,    user_id="user123",)
typescript
// TypeScript SDKimport { KlavisClient, McpServerName } from 'klavis';
const klavis = new KlavisClient({ apiKey: 'your-api-key' });
// Create Strata instanceconst strata = await klavis.mcpServer.createStrataServer({    userId: "user123",    servers: [Klavis.McpServerName.Gmail, Klavis.McpServerName.Slack],});
// Or use individual MCP serversconst gmail = await klavis.mcpServer.createServerInstance({    serverName: McpServerName.GMAIL,    userId: "user123"});

Option 4: REST API

bash
# Create Strata servercurl -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 servercurl -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

Made with ❤️ by the Klavis Team

Source: README.md at commit 45c9f7d

Tools

0
This server asks for a credential such as an API key, so SourceWeft could not read its tools without one and has not indexed them.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts