How to Use the Landbot MCP in Cursor

Q: How does the Landbot MCP Server work with Cursor?

You add the server details to your mcp.json file in your project. Once configured, you can switch Cursor's chat to Agent mode. The agent can then call any of the Landbot tools, like getcustomer or sendtextmessage, to get live data or perform actions.

Q: Can I use this to re-assign a bot conversation to a human agent from Cursor?

You can. The assignagent tool is designed for that. You can tell the agent to find a customer's conversation and then use that tool to transfer it from the bot to a live agent in Landbot.

Let Cursor's agent write your Landbot integration code using live customer data and bot info.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Landbot MCP to Cursor

Create your Vinkius account to connect Landbot to Cursor and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Landbot with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate code with real data

Stop writing boilerplate with placeholder IDs. Tell Cursor's agent to write a function that interacts with a Landbot customer. The agent can use `search_customers` to find a real user, then inject their actual ID into the generated code for a `send_text_message` call. What you get is code that works immediately. The agent isn't guessing; it's using the live context from your Landbot account. This turns a multi-step process of finding IDs and testing into a single prompt.

Debug bots inside your editor

When a bot is acting up, you need to see the conversation and its configuration. Instead of opening multiple tabs, just ask the agent. It can call `get_messages` to pull the full chat transcript and `get_bot` to fetch the bot's setup details. All that information appears directly in Cursor, right next to your code. You can see the conversation flow, check the bot's logic, and find the problem without breaking your focus. It's the fastest way to diagnose issues.

Script administrative Landbot tasks

You can automate tedious tasks across your Landbot user base. Tell the agent to build a script that finds stale conversations. It can `list_customers`, check their last interaction time, and then generate the code to `assign_agent` to a human for follow-up. This isn't just about one-off actions. Your agent can build repeatable scripts that use the full suite of tools. This MCP server gives Cursor the ability to read and act on your Landbot data, turning your ideas into working code.

Setup guide

Set up Landbot MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Landbot MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Landbot transactions." If the MCP tools are loaded correctly, Cursor will call the Landbot tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "landbot-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Landbot. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Landbot now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Landbot MCP in Cursor

You add the server details to your `mcp.json` file in your project. Once configured, you can switch Cursor's chat to Agent mode. The agent can then call any of the Landbot tools, like `get_customer` or `send_text_message`, to get live data or perform actions.

Yes, that's the main idea. You can ask it to, for example, "write a script that finds a customer by email and sends them a message." The agent will use `search_customers` and `send_text_message` to generate a working block of code.

Your agent can access anything the tools expose. This includes customer lists and metadata (`list_customers`, `get_customer`), bot configurations (`list_bots`, `get_bot`), and full conversation transcripts (`get_messages`).

You can. The `assign_agent` tool is designed for that. You can tell the agent to find a customer's conversation and then use that tool to transfer it from the bot to a live agent in Landbot.

The server processes your requests in an ephemeral environment. It only handles the specific Landbot data required for a tool call—like customer info or message content—and doesn't persist it. Each request is an isolated, short-lived transaction.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript