VibeKit MCP
MCP server for VibeKit — build, deploy, and manage hosted apps and chat with each app's persistent server-side AI agent from Claude Desktop, Cursor, or any MCP client. Every app gets its own agent and a live URL; bring your own Claude/OpenAI key or pay-as-you-go.
README
vibekit-mcp
MCP server for VibeKit, deploy apps, manage hosting, and chat with AI agents from any MCP client.
This package is for VibeKit cloud/API access. It does not connect your local Claude Code instance to Telegram. For local-machine remote control, use vibekit-agent.
Use it remotely (no install)
VibeKit also runs as a hosted remote server, so clients that accept a remote MCP URL (claude.ai web connectors, ChatGPT, etc.) need no install:
https://mcp.vibekit.bot/mcp?api_key=vk_your_api_key_here
Paste that URL into your client's "custom connector" / "remote MCP server" field. Clients that let you set headers can instead send Authorization: Bearer vk_your_api_key_here and use the bare https://mcp.vibekit.bot/mcp. Get a key from @the_vibe_kit_bot with /apikey.
Prefer a local stdio install (e.g. Claude Desktop)? Use the steps below.
Installation
npm install -g vibekit-mcp
Setup
-
Get a VibeKit API key:
- Open @the_vibe_kit_bot in Telegram
- Send
/apikeyto generate your key
-
Add to your MCP client config (e.g. Claude Desktop) (
~/Library/Application Support/Claude/claude_desktop_config.jsonon macOS):
{
"mcpServers": {
"vibekit": {
"command": "vibekit-mcp",
"env": {
"VIBEKIT_API_KEY": "vk_your_api_key_here"
}
}
}
}
- Restart your MCP client
Available Tools
Hosting
| Tool | Description |
|---|---|
vibekit_list_apps |
List all hosted apps |
vibekit_get_app |
Get details about a specific app |
vibekit_create_app |
Create new app from template |
vibekit_deploy |
Deploy GitHub repo to hosting |
vibekit_redeploy |
Redeploy app with latest code |
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 |
Agent
| Tool | Description |
|---|---|
vibekit_chat |
Chat with an app's AI agent |
vibekit_agent_status |
Get agent status |
vibekit_agent_history |
Get chat history with agent |
Database
| Tool | Description |
|---|---|
vibekit_enable_database |
Enable database for an app |
vibekit_database_status |
Get database status and connection info |
QA
| Tool | Description |
|---|---|
vibekit_run_qa |
Run automated QA tests |
vibekit_qa_status |
Get QA test results |
Tasks
| Tool | Description |
|---|---|
vibekit_submit_task |
Submit a coding task |
vibekit_get_task |
Get task status/result |
vibekit_list_tasks |
List recent tasks |
vibekit_wait_for_task |
Wait for task completion |
vibekit_create_schedule |
Create recurring scheduled task |
vibekit_list_schedules |
List scheduled tasks |
vibekit_delete_schedule |
Delete scheduled task |
Account
| Tool | Description |
|---|---|
vibekit_account |
Get account info (plan, credits, usage) |
vibekit_list_skills |
List implementation skills |
vibekit_get_skill |
Fetch specific skill content |
Example Usage
Once configured, you can use prompts like:
- "Deploy my GitHub repo to VibeKit and create a new app"
- "Chat with the AI agent for my app about adding a contact form"
- "Show me the logs for my app and restart it if there are errors"
- "Enable a database for my app and check its status"
- "Run QA tests on my deployed app"
- "Check my VibeKit account balance and list my apps"
- "Create a weekly schedule to improve my app's performance"
Environment Variables
| Variable | Description | Default |
|---|---|---|
VIBEKIT_API_KEY |
Your VibeKit API key (required) | — |
VIBEKIT_API_URL |
API base URL | https://vibekit.bot/api/v1 |
Related Packages
vibekit-cli: terminal client for VibeKit cloud workflowsvibekit-agent: Telegram bridge for local Claude Code on your own machine
Links
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。