Strata
- 5.8k repo stars
- Updated June 1, 2026
- Klavis-AI/klavis
Klavis Strata is a MCP server that enables progressive tool usage so coding agents can scale MCP integrations without overload, via hosted streamable-http.
About
Klavis Strata is a hosted Model Context Protocol server focused on progressive tool usage—helping AI coding agents work with growing MCP tool sets without drowning in irrelevant capabilities. developers often start with one or two integrations, then accumulate databases, browsers, payment, and ops servers; Strata targets that scaling pain by structuring how tools are exposed and selected over time. You connect via the streamable HTTP remote documented in the registry rather than maintaining a bespoke orchestration layer in every project. It sits in the build phase under agent-tooling because the value appears while you wire and expand your agent environment, though disciplined tool surfacing also pays off during ship and operate when incident response tools multiply. Strata is infrastructure for MCP ergonomics, not a replacement for individual domain servers like Git hosting or observability vendors.
- Strata MCP promotes progressive tool usage for large tool surfaces
- Hosted streamable-http endpoint at strata.klavis.ai
- Open-source Klavis monorepo on github.com/Klavis-AI/klavis
- Registry version 1.0.0; product positioning at klavis.ai
- Suited when solo builders accumulate many MCP servers in one agent
Strata by the numbers
- Data as of Jul 27, 2026 (Skillselion catalog sync)
claude mcp add --transport http strata https://strata.klavis.ai/mcp/Add your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| repo stars | ★ 5.8k |
|---|---|
| Transport | HTTP |
| Auth | None |
| Last updated | June 1, 2026 |
| Repository | Klavis-AI/klavis ↗ |
What it does
Scale how many MCP tools your agent can use progressively without overwhelming context or tool-selection noise.
Who is it for?
Best when you're stacking many MCP servers in Claude Code or Cursor and need saner tool progression.
Skip if: Projects with only one or two fixed tools that never change, or teams wanting a single vertical MCP (e.g. only Postgres).
What you get
After registering Strata, you get a klavis.ai-backed layer meant to stage and scale tool access as your MCP footprint grows.
- More manageable tool surface as MCP count grows
- Foundation for progressive discovery instead of flat tool dumps
- Hosted Strata endpoint wired into your agent configuration
By the numbers
- Registry server version 1.0.0
- Remote MCP URL: https://strata.klavis.ai/mcp/
- Upstream source: github.com/Klavis-AI/klavis
README.md
🎯 Choose Your Solution
StrataIntelligent connectors for your AI agent, optimize context window 
|
MCP Integrations100+ prebuilt integrations out-of-the-box, with OAuth support 
|
MCP Sandboxscalable MCP environments for LLM training and RL 
|
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
Made with ❤️ by the Klavis Team
Recommended MCP Servers
0piFree, 2hr expiry agent storage to cache contexts, bridge workflows, or dump data.
100Hires AI ATS & Recruitment SoftwareOfficial 100Hires MCP: AI ATS & Recruitment Software for candidates, jobs, applications, interviews.
123elec McpInterface MCP officielle du site marchand 123elec, catalogue, stock, panier, commandes.
1stayHotel booking MCP server.2
2D Assets MCPMCP server for generating advanced mock 2D PNG assets for game prototypes.43D MeshWeaverMesh spatial optimizer reducing geometric overhead in 3D assets.How it compares
MCP tool-orchestration layer, not a marketplace of unrelated skills or a lone SaaS API wrapper.
FAQ
Who is Klavis Strata for?
Developers running AI coding agents with large or growing MCP tool lists who want progressive exposure instead of dumping every tool at once.
When should I use Klavis Strata?
Use it during build (and as you add ops tools later) when tool count or complexity starts hurting agent reliability and latency.
How do I add Klavis Strata to my agent?
Register the streamable-http remote https://strata.klavis.ai/mcp/ in your MCP client and follow klavis.ai setup guidance for your agent stack.