Skip to content
MCP server

VibeKit

Deploy, monitor and run hosted web apps on VibeKit from any MCP client

Pricing
Freemium
Platforms
Web, iOS, CLI
Runs
Remotely
Version
0.8.2
Listing updated
3 days ago

About VibeKit

VibeKit is a freemium MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.

VibeKit hosts apps that each get their own persistent AI agent, and this server lets Claude Code, Cursor, Codex or any MCP client drive that platform. The tool list covers hosting, the per-app agent, Postgres databases, QA runs and long-running coding tasks.

On the hosting side an agent can create an app from a template, deploy a GitHub repo, redeploy, roll back to an earlier deploy, read logs, restart, stop or start, and read or set environment variables. Database tools enable Postgres for an app, show its schema and run read-only SELECT queries limited to 200 rows. Task tools submit, wait for and cancel coding tasks.

The remote endpoint takes an API key as a bearer header or in the URL, and a key can be created with one unauthenticated request that returns a free-plan account. Platform pricing is separate: the free plan has 10 AI sessions a month and 2 workspaces, and AI usage can be your own provider key or credits.

Install

Run in a terminal

claude mcp add --transport http vibekit-mcp https://mcp.vibekit.bot/mcp

Add to Settings → Connectors → Add custom connector

https://mcp.vibekit.bot/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "vibekit-mcp": {
      "url": "https://mcp.vibekit.bot/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "vibekit-mcp": {
      "type": "http",
      "url": "https://mcp.vibekit.bot/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "vibekit-mcp": {
      "serverUrl": "https://mcp.vibekit.bot/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "vibekit-mcp": {
      "type": "http",
      "url": "https://mcp.vibekit.bot/mcp"
    }
  }
}

Tools this server provides (30)

Taken from the project documentation; the running server may differ.

vibekit_list_apps
List all hosted apps
vibekit_get_app
Get details about a specific app
vibekit_list_templates
List starter templates
vibekit_create_app
Create a new app from a template
vibekit_deploy
Deploy a GitHub repo to hosting
vibekit_redeploy
Redeploy an app with the latest code
vibekit_list_deploys
List an app's recent deploys with status and commit
vibekit_rollback_deploy
Roll an app back to a previous deploy
vibekit_app_logs
Get application logs
vibekit_restart_app
Restart an app
vibekit_stop_app
Stop an app
vibekit_start_app
Start a stopped app
vibekit_app_env
Get app environment variables
vibekit_set_env
Set app environment variables
vibekit_delete_app
Delete an app permanently
vibekit_chat
Chat with an app's AI agent
vibekit_agent_status
Get agent status
vibekit_agent_history
Get chat history with the agent
vibekit_enable_database
Enable a Postgres database for an app
vibekit_database_status
Get database status and connection info
vibekit_db_schema
Get the database schema
vibekit_db_query
Run a read-only SQL query, SELECT only, up to 200 rows
vibekit_db_table
Browse one table's rows with pagination and sorting
vibekit_run_qa
Run automated QA tests
vibekit_qa_status
Get QA test results
vibekit_submit_task
Submit a coding task
vibekit_get_task
Get task status or result
vibekit_list_tasks
List recent tasks
vibekit_wait_for_task
Wait for task completion
vibekit_cancel_task
Cancel a running task

What it does

App lifecycle tools
Create, deploy, redeploy, roll back, restart, stop and start apps.
Logs and environment
Read application logs and get or set environment variables.
Per-app agent chat
Talk to an app's persistent agent and read its status and history.
Postgres access
Enable a database, view its schema and run read-only queries.
QA and tasks
Run QA tests and manage long-running coding tasks.
Remote or local
Hosted endpoint, or an npm package for stdio clients.

Good for

  • Have Claude Code deploy a GitHub repo and return a live URL
  • Roll back a bad deploy from a chat
  • Inspect a database schema without leaving the editor
  • Set an environment variable and restart the app
  • Run automated QA after a change

Pricing

Freemium

Free plan with 10 AI sessions a month; paid plans include $3, $20 or $25 of monthly credit; credit top-ups from $10

Prices change. Check vibekit.bot before you buy.

VibeKit FAQ

How do I get an API key?

One POST to /api/v1/auth/register returns a vk_ key on a free plan, or copy one from your profile.

Can I use it without installing?

Yes, clients that accept a remote URL can use https://mcp.vibekit.bot/mcp.

Can the database tool write?

vibekit_db_query is read-only, SELECT only, up to 200 rows.

What does the platform cost?

A free tier exists; paid plans include monthly credit of $3, $20 or $25.

Is VibeKit free?

VibeKit has a free plan, with paid plans for more usage or features.

How do I add VibeKit to Claude Code?

Run this command in your terminal: claude mcp add --transport http vibekit-mcp https://mcp.vibekit.bot/mcp

What are the best alternatives to VibeKit?

The closest alternatives to VibeKit are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to VibeKit

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools