How to Use the Landbot MCP in Google ADK

Q: How can I use Google ADK to assign a Landbot agent based on data in BigQuery?

First, your agent finds the user with searchcustomers. Then, it queries BigQuery with that user's info. Finally, based on the BigQuery results, it selects an agent ID and calls assignagent in Landbot.

Q: Can a Gemini agent read a Landbot customer's entire chat history with Google ADK?

Yes, within the API's limits. The getmessages tool fetches the chat history for a specific customer. Gemini's large context window is perfect for processing this transcript to understand the full situation.

Q: What's the process for sending a message to a Landbot user with a Google ADK agent?

Your agent identifies the target user via getcustomer or searchcustomers. Then, it calls the sendtextmessage tool with the customer's ID and the message content. It's a single API call through the MCP.

Q: How does this Landbot MCP server help with analyzing support trends?

Your agent can periodically call listcustomers and getmessages to collect raw conversation data. You can then have the agent push this data to a BigQuery table for long-term analysis with your existing BI tools.

Connect Google ADK agents to Landbot for enterprise-scale conversational AI. Act on your customer data from Google Cloud.

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 Google ADK

Create your Vinkius account to connect Landbot to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Link BigQuery Insights to Live Chats

Your Gemini agent can pull customer data from Landbot. Use `search_customers` or `get_customer` to get a user's ID, then feed that ID into a BigQuery lookup. Now your agent has both chat history and your internal customer profile. This changes how you support people. An agent can check `get_messages` for recent issues, cross-reference the user's purchase history from your data warehouse, and then use `send_text_message` to offer a genuinely personalized solution.

Build Data-Driven Routing with Google ADK

Use the `list_bots` and `list_customers` tools to get a high-level view of your support operations. Your Google ADK agent can analyze this data, maybe even pipe it to Vertex AI for trend analysis. It’s about seeing the whole picture. Based on that analysis, the agent can take action. It can programmatically use `assign_agent` to re-route a whole segment of customers to a specialized team, all without a human clicking a button. This is how you manage support queues at enterprise scale.

Your Gemini Agent Manages the MCP Server

Give your agent control over the bot infrastructure. It can call `list_bots` to see what's active and `get_bot` to understand the specific purpose and configuration of each one. With this information, your agent running on Google ADK can build dynamic workflows. Imagine an agent that automatically routes users to the most appropriate bot based on their language or question complexity, all powered by Gemini's reasoning over the data from this MCP server.

Setup guide

Set up Landbot MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Landbot tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Landbot_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Landbot tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

First, your agent finds the user with `search_customers`. Then, it queries BigQuery with that user's info. Finally, based on the BigQuery results, it selects an agent ID and calls `assign_agent` in Landbot.

Yes, within the API's limits. The `get_messages` tool fetches the chat history for a specific customer. Gemini's large context window is perfect for processing this transcript to understand the full situation.

Your agent identifies the target user via `get_customer` or `search_customers`. Then, it calls the `send_text_message` tool with the customer's ID and the message content. It's a single API call through the MCP.

Your agent can periodically call `list_customers` and `get_messages` to collect raw conversation data. You can then have the agent push this data to a BigQuery table for long-term analysis with your existing BI tools.

The server processes customer identifiers and message text from tools like `get_messages`. All data transits through a zero-trust, ephemeral environment on Vinkius. Authentication is managed by a single, revocable token for the MCP endpoint.

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