mcpField
T
Typebot Mcp Server

Typebot Mcp Server

Local
github.com/osdeibiBusiness & Marketing5Updated 68w ago

About Typebot Mcp Server

An MCP server that makes Typebot’s REST API callable through natural-language commands. It is for Typebot workspace users managing bots, conversation results, and chat sessions from Claude Desktop or another MCP client.

Key features

  1. 01Create, list, retrieve, update, and delete Typebots
  2. 02Publish and unpublish Typebots
  3. 03Retrieve conversation results
  4. 04Start Typebot chat sessions

Use cases

  1. 01Create or revise a workspace Typebot
  2. 02Change a Typebot’s published state
  3. 03Review a bot’s conversation results
  4. 04Start a chat session with a Typebot

MCP support

Runs over STDIO and exposes Typebot REST API operations as tools for Claude Desktop and other MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP-Typebot

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

  1. Node.js 18+
  2. A valid Typebot API token and workspace ID
  3. Claude Desktop connected to your local MCP server

Installation

git clone <repo-url>
cd mcp-typebot
npm install
npm run build

You can also install the published package directly via npm:

npm install mcp-typebot
npm start

Running

npm start

This starts the MCP server on STDIO. Claude Desktop (or any MCP client) will connect to it automatically.


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.ts and registering them in src/index.ts.
  • Define a Zod schema for each tool to get automatic prompting and validation.

License


Configuring Claude Desktop

To connect Claude Desktop to this MCP server, add the following to your Claude configuration (e.g. claude_desktop_config.json):

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

Make sure the command and args point to your local built index.js, and that your .env values match those in env.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.