VibeKit MCP Server

A Model Context Protocol server that lets Claude Desktop, Cursor, Zed, Continue or any other MCP client operate your VibeKit account directly. Deploy GitHub repos, set env vars, tail logs, query an app's database, chat with each app's agent. Tell Claude "deploy this and set the API key"; Claude does it.

Remote connector, no install

For clients that take a remote MCP URL (claude.ai web connectors, ChatGPT, and more), there's nothing to install, just paste this URL:

https://mcp.vibekit.bot/mcp?api_key=vk_your_api_key_here

Clients that let you set headers can use the bare https://mcp.vibekit.bot/mcp with Authorization: Bearer vk_your_api_key_here. Copy your key from Profile in the iOS app or in the web dashboard (app.vibekit.bot/profile).

Already added a vibekit server, or rotating your key? Prefer the header form. Because the ?api_key= URL bakes the key into the endpoint, changing keys means replacing the whole server entry, and some clients keep the old one until you explicitly overwrite it, so you can end up authenticating with a stale key without noticing. With the bare URL + Authorization: Bearer header (or the VIBEKIT_API_KEY env var for local/stdio), the endpoint never changes, so rotating a key is just swapping the header value. If your client added the URL form, delete the existing vibekit entry before re-adding rather than adding a second one.

Install (local / stdio)

Prefer running it locally (e.g. Claude Desktop, Cursor)?

npm install -g vibekit-mcp

It reads your VibeKit API key from the VIBEKIT_API_KEY env var. Keys start with vk_; copy yours from Profile in the iOS app or the web dashboard.

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_your_api_key_here"
      }
    }
  }
}

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

Configure Cursor

Add the same vibekit entry to ~/.cursor/mcp.json (every project) or .cursor/mcp.json (one project), with the same command and env var.

What you can do

36 tools exposed today, grouped by surface:

Hosting & Apps

AI Agent

Database

QA

Tasks

Schedules

Account

Skills

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, links your computer to the iPhone app so you can run Claude Code or Codex on it from your phone
• vibekit-cli, terminal CLI for kicking off agent tasks and scheduling cron jobs

FAQ