Varity MCP Server
Enables AI coding tools to scaffold, build, and deploy Node.js or Python apps to Varity with a single command, automatically provisioning databases and backend services.
README
Varity MCP Server
Deploy any Node or Python app, AI agent, or LLM straight from your AI coding tool — one command, live in 60 seconds.
@varity-labs/mcp is the Model Context Protocol server for Varity. It gives AI coding tools — Claude Code, Cursor, Codex, Windsurf — the tools to scaffold, build, and deploy your app for you. Ask your editor to ship your project and it goes from local code to a live URL, with the database and backend services it needs wired automatically.
Varity is a fixed monthly cost per app, 60-80% cheaper than Vercel, Render, or Railway — your bill does not change with traffic.
Install
Add the server to your AI tool's MCP config:
{
"mcpServers": {
"varity": {
"command": "npx",
"args": ["-y", "@varity-labs/mcp@beta"]
}
}
}
- Claude Code:
claude mcp add varity -- npx -y @varity-labs/mcp@beta - Cursor / Windsurf / Codex: add the JSON above to your MCP settings.
Then ask your editor: "Deploy this app with Varity."
What you can do
Once connected, your AI tool can:
- Deploy your code —
varitykit app deployequivalent, one step, returns a live URL - Estimate cost before you ship, with the built-in calculator
- Migrate from Vercel in seconds
- Deploy curated AI agent templates with one command
- Scaffold, build, and run projects locally
Tool surface
The public server exposes these tools (stdio transport):
| Group | Tools |
|---|---|
| Discovery | varity_search_docs, varity_cost_calculator, varity_doctor |
| Scaffold & setup | varity_init, varity_install_deps, varity_build, varity_login |
| Deploy your code | varity_deploy, varity_deploy_status, varity_deploy_logs, varity_delete_deployment, varity_create_repo, varity_migrate |
| AI agent templates | varity_list_agents, varity_agent_info, varity_deploy_agent |
| Local dev (stdio only) | varity_open_browser, varity_dev_server |
Full reference: docs.varity.so/ai-tools/mcp-server-spec.
Supported frameworks
Node.js (Next.js, React, Vue, Astro, Qwik, Vite SPA, Express, Fastify, NestJS, Koa, Hono), Python (FastAPI, Django, Flask), and static sites. Auto-wired backend services: Postgres (with pgvector), Redis, MongoDB, MySQL, and Ollama.
Local development
npm install
npm run build # compile to dist/
npm run dev # run the server in watch mode
npm test # vitest
Links
- Docs: docs.varity.so
- Discord: discord.gg/7vWsdwa2Bg
- X / Twitter: @VarityHQ
- Website: varity.so
License
MIT © Varity Labs. See LICENSE.
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.