Strata

Strata

Strata is a native MCP server that gives agents verified intelligence across 22 AI ecosystems. Tools: * get_best_practices * get_latest_news * get_top_integrations * search_ecosystem * find_mcp_servers * Claude-validated content, injection-safe by design * Refreshed twice daily via automated pipeline * Works with Claude Code, Cursor, Windsurf, Cline * Free tier available Site: https://usestrat

Category
Visit Server

README

Strata

AI ecosystem intelligence for agents. One endpoint, 22+ AI ecosystems, machine-readable best practices, news, and integrations — delivered as both a REST API and a native MCP server.

Live: usestrata.dev · Docs: usestrata.dev/docs

What it does

Agents need current, structured knowledge about the AI tools they work with. Strata provides that knowledge across 22 ecosystems (Claude, OpenAI, Gemini, Cursor, Windsurf, LangChain, Vercel AI SDK, and more) via:

  • GET /api/v1/best-practices — verified best practices, optionally filtered by category
  • GET /api/v1/news — latest news (real-time on Pro, 24h delayed on Free)
  • GET /api/v1/integrations — top integrations and MCP servers, optionally by use case
  • GET /api/v1/search — full-text search across all content
  • POST /mcp — same data exposed as MCP tools (get_best_practices, get_latest_news, get_top_integrations, search_ecosystem, list_ecosystems)

Content is refreshed continuously: feeds are scraped, validated by Claude for relevance, deduplicated, and written to Postgres. Best practices are regenerated when stale.

Quick start

Sign up at usestrata.dev/signup for an API key.

REST:

curl -H "X-API-Key: sk_your_key" \
  "https://www.usestrata.dev/api/v1/best-practices?ecosystem=claude"

MCP (Claude Code):

claude mcp add strata --transport http \
  https://www.usestrata.dev/mcp \
  --header "Authorization: Bearer sk_your_key"

MCP (Claude Desktop, Cursor, Windsurf, Cline):

{
  "mcpServers": {
    "strata": {
      "url": "https://www.usestrata.dev/mcp",
      "headers": {
        "Authorization": "Bearer sk_your_key"
      }
    }
  }
}

Free tier: 100 calls/month, free ecosystems only. Pro tier: 10,000 calls/month, all ecosystems, real-time news.

Tech stack

  • Next.js 16 (App Router, Turbopack)
  • Supabase — Postgres + auth, RLS-enforced
  • Stripe — subscriptions
  • Anthropic Claude — content validation + best-practice generation in the refresh pipeline
  • MCP SDK@modelcontextprotocol/sdk with WebStandardStreamableHTTPServerTransport

Local development

Requires Node 20+ and a .env.local with the variables documented in CLAUDE.md.

npm install
npm run dev      # http://localhost:3000
npm run build    # production build
npm run lint     # ESLint
npm run refresh  # populate content_items from sources (requires ANTHROPIC_API_KEY)
npm run mcp      # stdio MCP transport for local clients

Architecture, auth model, refresh pipeline, and design system are all documented in CLAUDE.md. Migrations live in supabase/migrations/.

Repository status

Source-available for transparency. Not currently accepting external pull requests — feedback and bug reports are welcome via GitHub Issues.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured