广告合作
MCP.so
登录
T

Typebot MCP Server

@osdeibi

代码仓库

基本信息

分类

其他

传输方式

stdio

作者

osdeibi

提交者

Osdeibi Acurero

关于 Typebot MCP Server

A small MCP server that exposes Typebot’s REST API as callable tools in Claude Desktop (via STDIO).

#typebot#claude#chatbots

Typebot MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mcp-typebot": {
      "command": "node",
      "args": [
        "path/to/project/dist/index.js"
      ],
      "env": {
        "TYPEBOT_TOKEN": "YOUR_TOKEN_HERE",
        "TYPEBOT_WORKSPACE_ID": "YOUR_WORKSPACE_ID"
      }
    }
  }
}

Typebot MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Typebot MCP Server?

Typebot MCP Server is a Model Context Protocol server that gives AI assistants direct access to the Typebot conversational form builder API. It enables managing Typebots — creating, reading, updating, deleting, publishing, unpublishing, retrieving results, and starting chat sessions — all through natural language commands in Claude Desktop or compatible MCP clients. It is aimed at developers and NoCode builders who want to control their Typebot workspace without leaving their AI interface.

How to use Typebot MCP Server?

Install with git clone, npm install, and npm run build. Configure a valid Typebot API token and workspace ID. Use Claude Desktop connected to the local MCP server, then invoke any tool like createBot, listBots, getBot, updateBot, deleteBot, publishBot, unpublishBot, listResults, or startChat.

Key features of Typebot MCP Server

  • Create new Typebots in a workspace
  • List all Typebots in a workspace
  • Fetch a single Typebot by its ID
  • Patch an existing Typebot (rename, etc.)
  • Delete a Typebot by its ID
  • Publish or unpublish a Typebot
  • Retrieve conversation results from a Typebot
  • Start a new chat session with a Typebot

Use cases of Typebot MCP Server

  • Build and iterate on conversational forms directly from an AI assistant
  • Automate Typebot workspace management without leaving the chat interface
  • Quickly fetch results from published Typebots for analysis or reporting
  • Start and manage chat sessions with Typebots during development

常见问题

1

How do I configure the server?

You need a valid Typebot API token and workspace ID set in the environment. The README does not specify exact environment variable names, but both are required at runtime.

2

What are the runtime requirements?

Node.js 18+ is required. The server is built with Node.js and the MCP SDK.

3

Where does my data live?

Typebot data lives entirely on Typebot’s cloud infrastructure. The MCP server acts as a bridge and does not store any data locally beyond the MCP session.

4

Does the server support authentication?

The server uses a Typebot API token for authorization. The README does not mention any additional authentication layer for the MCP transport itself.

5

What is the transport mechanism?

The server communicates via the Model Context Protocol (MCP) with Claude Desktop. The README does not specify whether it uses stdio or HTTP transport.

评论

其他 分类下的更多 MCP 服务器

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K

The Living Bread

The Living Bread

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w

Health by Dr Brad

Dr Brad Stanfield

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K
广告合作