Varity

Deploy Node and Python apps, AI agents, and LLMs to production from your AI editor, manage live deployments, and estimate the monthly cost before you deploy.

Documentation

@varity-labs/mcp

npm License: MIT Status: Beta

The published Varity MCP package for Cursor, Claude Code, VS Code, Windsurf, and other MCP clients.

This repository contains only @varity-labs/mcp, the npm MCP server. It is a thin tool wrapper around varitykit and Varity's gateway APIs; it is not the Python CLI, the portal, the dormant SDK, or an app-store package.

The Varity MCP Server lets a supported local AI coding client build, deploy, and manage supported apps in production for you.

Quick start: pick your editor below and run one command.

Install

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "varity": {
      "command": "npx",
      "args": ["-y", "@varity-labs/mcp"]
    }
  }
}

Claude Code

claude mcp add varity -- npx -y @varity-labs/mcp

VS Code with Copilot

  1. Command Palette → MCP: Add Server
  2. Select Command (stdio)
  3. Command: npx -y @varity-labs/mcp
  4. Name: Varity

Windsurf

Add to mcp_config.json:

{
  "mcpServers": {
    "varity": {
      "command": "npx",
      "args": ["-y", "@varity-labs/mcp"]
    }
  }
}

Any MCP-compatible client (stdio)

{
  "mcpServers": {
    "varity": {
      "command": "npx",
      "args": ["-y", "@varity-labs/mcp"]
    }
  }
}

What you can do from your AI editor

The MCP exposes Varity's deploy surface so your AI tool can take action — not just generate code. Try prompts like:

Deploy your own code

  • "Deploy this project to production"
  • "Ship this app live"
  • "What would it cost to deploy this on Varity?"

Deploy a supported public template (one command, no code required)

  • "What templates can Varity deploy?"
  • "Which templates need no secrets?"
  • "Deploy this public, secret-free template for me"

Manage live deployments

  • "Show my deployments"
  • "What's the URL of my last deploy?"
  • "Stop my-app and stop billing it"
  • "Get the build logs for my deployment"

Preview a Vercel migration

  • "Preview what would change when migrating github.com/me/my-app"
  • "Show me the Vercel-specific artifacts to replace"

Docs and pricing

  • "Search Varity docs for environment variables"
  • "What is the current estimate for this pricing profile?"
  • "What billing projection does my deployed app report?"

Tools

ToolWhat it does
varity_search_docsSearch the Varity documentation
varity_cost_calculatorProject the live owner's monthly or hourly USD estimate without converting units; pre-deploy estimates need no sign-in
varity_balanceRead your available balance, authorization maximum (reserved_usd) and amount owed as exact decimal USD strings using your deploy key; the authorization maximum is not funded backing, and unavailable reads never become zero
varity_doctorCheck that your environment is ready to deploy
varity_loginCheck authentication and route login through the trusted varitykit auth login terminal flow
varity_install_depsInstall project dependencies
varity_buildBuild the project
varity_open_browserOpen a URL locally
varity_dev_serverStart the local development server
varity_create_repoCreate a GitHub repository and push the project
varity_deployDeploy the current project to production
varity_deploy_statusCheck the status of a deployment
varity_deploy_logsRead build and runtime logs
varity_delete_deploymentRequest deletion; poll varity_deploy_status until it is deleted and billing is stopped
varity_set_envPreserve the public tool route while refusing secret values and directing configuration to a secret-safe interface
varity_redeployReapply an existing deployment's saved configuration; unchanged input may be a no-op
varity_machines_listList your CPU virtual machines (optionally the CPU VM profile catalog)
varity_machines_createQuote and create a CPU virtual machine with your SSH public key
varity_machines_deleteDelete a CPU virtual machine and confirm its billing stopped
varity_list_templatesList certified gateway-owned Varity templates
varity_template_infoShow full details for one certified template
varity_deploy_templateDeploy a public certified template with no required secrets; refuse private or secret-bearing templates
varity_list_agentsBackward-compatible alias for varity_list_templates
varity_agent_infoBackward-compatible alias for varity_template_info
varity_deploy_agentBackward-compatible alias for varity_deploy_template
varity_migratePreview Vercel-to-Varity source transformations without mutating or deploying

Templates

Varity templates come from the gateway-owned certified catalog. Ask your AI editor "what templates can I deploy?" and it will list the live catalog and inspect each template contract. The MCP deploy tool supports only public templates that declare no required environment variables; it refuses private or secret-bearing templates and routes those through an approved secret-safe interface.

Each template reserves different hardware. Use varity_template_info to see the required environment variables, private/public access mode, resources, hardware profile, and certification state before deciding whether the MCP can deploy it.

End-to-end example

From empty folder to deployed app, all in natural language:

You: "Make me a simple landing page for my coffee shop and deploy it"
AI:  Wrote the landing page and ran its local build.
AI:  Deploy accepted. Tracking its durable run until the owner reports a terminal outcome.
AI:  The status owner now reports the app live at https://varity.app/coffee-shop/

You: "Now deploy Agent Zero"
AI:  Agent Zero is certified and does not require environment variables.
AI:  Template deploy accepted. No live URL is claimed until varity_deploy_status proves it.

Pricing

Pricing profiles and values are owned by Varity's live public interface. Ask your AI editor to use varity_cost_calculator for a current estimate; this package intentionally embeds no price table or billing-policy copy.

Transport

The package supports stdio for local MCP clients such as Cursor, Claude Code, VS Code, and Windsurf.

npx -y @varity-labs/mcp

The former hosted endpoint and network transport are retired. Browser clients that require a remote MCP URL are not supported by this package.

Prerequisites

  • Node.js >= 22.11 (the current supported LTS baseline; EOL Node 18/20 are unsupported)
  • For deployment: pip install varitykit

Deploy supported apps from your AI coding tool.

Documentation · GitHub · Discord