Typebot MCP Server
Enables interaction with Typebot's REST API to create, manage, publish, and chat with Typebots, and retrieve conversation results through natural language commands.
README
Typebot MCP Server
A small MCP server that exposes Typebot's REST API as callable tools in Claude Desktop and other MCP clients (via Streamable HTTP transport). You can create, list, get, update, delete, publish/unpublish Typebots, list results, and start chats—using natural-language commands.
Features
-
createBot
Create a new Typebot in your workspace.
Required:name
Optional:workspaceId,description -
listBots
List all Typebots in your workspace.
Optional:workspaceId -
getBot
Fetch a Typebot by its ID.
Required:botId -
updateBot
Patch an existing Typebot (e.g. rename).
Required:botId,typebot(object with fields to change)
Optional:overwrite -
deleteBot
Delete a Typebot by its ID.
Required:botId -
publishBot / unpublishBot
Toggle a Typebot’s published state.
Required:botId -
listResults
Retrieve conversation results for a Typebot.
Required:botId
Optional:limit,cursor,timeFilter,timeZone -
startChat
Begin a new chat session with a Typebot.
Required:botId
Optional:chat.context
Prerequisites
- Node.js 18+
- A valid Typebot API token and workspace ID
- Claude Desktop connected to your local MCP server
Installation
Option 1: Clone the repository
git clone <repo-url>
cd typebot-mcp
npm install
npm run build
Option 2: Install via npm
npm install typebot-mcp
npm run dev # for development
# or
npm run build # for production build
Option 3: Install via Smithery
You can easily install this MCP server through Smithery:
- Visit https://smithery.ai/server/@hithereiamaliff/typebot-mcp
- Follow the installation instructions on the Smithery page
- Configure your environment variables as described in the Deployment Options section
Running
Development Mode
npm run dev
This will start the server in development mode with hot reloading using Smithery CLI.
Production Build
npm run build
This will create a production build using Smithery CLI.
Usage in Claude Desktop
Simply write natural commands like:
User: “Create me a new typebot”
Claude: “Sure—what name?”
User: “MyDemoBot”
Claude (internally invokes):@createBot {"name":"MyDemoBot"}
Or, explicitly:
@updateBot {"botId":"<your_bot_id>","typebot":{"name":"NewName"},"overwrite":true}
You can also start a chat:
@startChat {"botId":"<your_bot_id>"}
Extending
- Add new tools by implementing them in
src/tools/bots.tsand registering them insrc/index.ts. - Define a Zod schema for each tool to get automatic prompting and validation.
Deployment Options
Local Configuration (Claude Desktop)
To connect Claude Desktop to this MCP server locally, you can run it in development mode and use the HTTP URL:
npm run dev
This will start the server on http://localhost:8181 by default. You can then add this URL to your Claude Desktop configuration.
Smithery Deployment
To deploy this MCP server on Smithery:
- Push your code to a GitHub repository
- Log into your Smithery account
- Create a new deployment and connect it to your GitHub repository
- Configure the following environment variables in Smithery:
TYPEBOT_TOKEN: Your Typebot API tokenTYPEBOT_WORKSPACE_ID: Your Typebot workspace IDTYPEBOT_API_URL: The full URL to your Typebot API including the /api/v1 path (e.g., https://your-typebot-domain.com/api/v1)
- Deploy the application
- Use the provided URL to connect Claude to your MCP server
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgements
This project is a direct fork of osdeibi's MCP-typebot. It builds upon the original work with the following improvements:
- Configurable API URL: Added support for custom Typebot API endpoints via the
TYPEBOT_API_URLenvironment variable instead of hardcoded URLs - Improved Error Handling: Enhanced error messages and validation in English
- Better Configuration: More flexible configuration options for different Typebot instances
- Code Quality: Various code improvements and optimizations
Migration from STDIO to HTTP Transport
This MCP server has been migrated from the deprecated STDIO transport to the recommended Streamable HTTP transport using the Smithery CLI. This migration provides several benefits:
- Better Scalability: HTTP transport allows for multiple concurrent connections
- Improved Reliability: Avoids issues with process management and IPC
- Enhanced Monitoring: Better logging and debugging capabilities
- Future Compatibility: Ensures compatibility with future MCP clients and standards
The migration was completed before the September 7, 2025 deadline set by Smithery for discontinuing STDIO transport support.
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。