VibeKit MCP Server

A Model Context Protocol server that lets Claude Desktop, Cursor, Zed, Continue — any MCP client — operate your VibeKit account directly. Deploy GitHub repos, set env vars, tail logs, chat with hosted agents. Tell Claude "deploy this and set the API key"; Claude does it.

Install

npm install -g vibekit-mcp

Latest published version: [email protected]. Get a VibeKit API key from app.vibekit.bot → Settings → API.

Configure Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or the equivalent on Windows / Linux:

{
  "mcpServers": {
    "vibekit": {
      "command": "vibekit-mcp",
      "env": {
        "VIBEKIT_API_KEY": "vk_live_..."
      }
    }
  }
}

Restart Claude Desktop. The new tools appear under the connectors icon.

Configure Cursor

Cursor → Settings → Features → Model Context Protocol → Add a new MCP server. Same command + env vars.

What you can do

31 tools exposed today, grouped by surface:

Hosting & Apps

vibekit_list_apps

List all hosted apps in your VibeKit account.

vibekit_get_app

Get details about a specific hosted app.

vibekit_create_app

Create a new hosted app from a template.

vibekit_list_templates

List available templates for vibekit_create_app (e.g. landing, dashboard, blog, saas, crud-api).

vibekit_deploy

Deploy a GitHub repo to VibeKit hosting.

vibekit_redeploy

Redeploy an existing hosted app to update it with latest code.

vibekit_app_logs

Get application logs for debugging and monitoring.

vibekit_restart_app

Restart a hosted app.

vibekit_stop_app

Stop a hosted app.

vibekit_start_app

Start a stopped hosted app.

vibekit_app_env

Get environment variables for a hosted app.

vibekit_set_env

Set environment variables for a hosted app.

vibekit_delete_app

Delete a hosted app permanently.

AI Agent

vibekit_chat

Chat with an app's AI agent. The agent can read, write, and modify the app's code.

vibekit_agent_status

Get the status of an app's AI agent.

vibekit_agent_history

Get chat history with an app's AI agent.

Database

vibekit_enable_database

Enable database for a hosted app.

vibekit_database_status

Get database status and connection info for an app.

QA

vibekit_run_qa

Run automated QA tests on a hosted app.

vibekit_qa_status

Get QA test results and status for an app.

Tasks

vibekit_submit_task

Submit a coding task to VibeKit. The AI will write code, commit to GitHub, and deploy to {subdomain}.vibekit.bot. Returns a task ID to poll for results.

vibekit_get_task

Get the status and result of a previously submitted task.

vibekit_list_tasks

List recent tasks submitted to VibeKit.

vibekit_wait_for_task

Wait for a task to complete and return the result. Polls every 5 seconds up to the timeout.

vibekit_cancel_task

Cancel a running task by ID. No-op for tasks that have already completed.

Schedules

vibekit_create_schedule

Create a scheduled recurring task. The AI will run this task automatically on the specified schedule.

vibekit_list_schedules

List all scheduled tasks.

vibekit_delete_schedule

Delete a scheduled task.

Account

vibekit_account

Get VibeKit account info including plan, credits balance, and usage.

Skills

vibekit_list_skills

List all available implementation skills. Returns skill IDs, names, descriptions, and tags. Use this to discover what skills are available before fetching specific ones.

vibekit_get_skill

Fetch the full content of a specific skill. Skills contain implementation patterns, code examples, and best practices for a domain. Fetch skills on-demand when you need guidance on a specific topic.

Why this beats the dashboard

Stay in your editor. No tab-switching. Deploy from inside the same chat you're writing the code in.
Compositional. Claude can chain calls — "deploy this, wait for it to come up, then set these 3 env vars, then restart" — without you nursing each step.
Scriptable from agents. If you have a Claude Code workflow that needs to deploy a sibling app, MCP makes it one tool call.

Related packages

vibekit-agent — run on your laptop to be a remotely-controllable Claude Code worker (iOS Remote Agent path)
vibekit-cli — terminal CLI for kicking off agent tasks and scheduling cron jobs

FAQ

What does the VibeKit MCP server do?

It exposes your VibeKit account as tools that any MCP client (Claude Desktop, Cursor, Zed, Continue, etc.) can call. You tell Claude Desktop 'deploy this repo and set OPENAI_API_KEY' and Claude actually does it via the MCP tools — no copy-pasting URLs into a separate dashboard.

How do I install vibekit-mcp?

Run `npm install -g vibekit-mcp` then add it to your Claude Desktop / Cursor MCP config. For Claude Desktop, edit ~/Library/Application Support/Claude/claude_desktop_config.json and add vibekit-mcp under mcpServers. The server uses your VibeKit API key for auth — get one from app.vibekit.bot/settings.

Which clients support this?

Any client that implements the Model Context Protocol spec — currently Claude Desktop, Cursor, Zed, Continue, and a growing list. The server uses stdio transport so it works with the standard MCP config block any of them accept.

Is the MCP server free?

Yes — the npm package is free and open-source. VibeKit's free tier (1 hosted app) is enough to start. The MCP server is just a thin RPC layer; your usage is bounded by your VibeKit plan and your client's own model costs.

Install vibekit-mcp in 60 seconds

npm i -g vibekit-mcp · paste API key · restart Claude Desktop / Cursor

Get an API key →