How to Use the Appcues MCP in Google ADK

Q: How do I integrate Appcues with Google ADK?

Install google-adk and initialize a McpToolset using your Vinkius HTTP endpoint URL. Pass this toolset to your LlmAgent configuration.

Q: Can Google ADK read my Appcues user profiles?

Yes. The agent calls getuserprofile to pull individual records. You can feed this data into Gemini to generate personalized messaging strategies.

Q: What Appcues flow data can this MCP Server access for Google ADK?

Your agent can pull the full directory with listflows and get granular details via getflow. It also has access to listmobileexperiences for mobile app tours.

Q: How do I track events in Appcues using Google ADK?

Use the trackuseractivity tool. Your agent formats the event data as JSON and sends it over. This is perfect for logging actions that happen outside your frontend application.

Give your Google ADK agents direct access to Appcues to read segment data and publish onboarding flows based on BigQuery analytics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Appcues MCP to Google ADK

Create your Vinkius account to connect Appcues 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 Appcues with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Appcues segments with Google ADK

Gemini agents call `list_segments` to cross-reference your BigQuery telemetry with active Appcues targeting. Enterprise teams already have their core data in Google Cloud. Now your system pulls the exact audience rules defining your in-app campaigns using `get_segment`. Because Gemini handles massive context windows, you feed thousands of segment definitions into a single prompt. The agent reads the output from the MCP Server, compares it against your Vertex AI models, and identifies overlapping user cohorts.

Manage user flows via MCP Server

Your automated systems check the current state using `list_flows` to control the lifecycle of your product tours. The agent knows exactly which tooltips and modals are live across your web application. It grabs granular details via `get_flow`. When a new feature rollout hits your pipeline, the agent triggers `publish_flow` to activate the corresponding experience. If a bug appears in production, it immediately executes `unpublish_flow` to hide the broken tour from users.

Sync user profiles and activities

Your agent uses `track_user_activity` to push profile updates based on backend events processed by Google Cloud. The payload accepts standard JSON strings. Sometimes you need to update user states without touching the frontend. To verify the update worked, the agent runs `get_user_profile`. It also pulls mobile-specific campaigns via `list_mobile_experiences` or web tasks with `list_checklists`. This keeps your cross-platform messaging perfectly aligned with your enterprise backend.

Setup guide

Set up Appcues 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 Appcues 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="Appcues_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Appcues 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 Appcues. 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 Appcues 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 Appcues MCP in Google ADK

Install `google-adk` and initialize a `McpToolset` using your Vinkius HTTP endpoint URL. Pass this toolset to your `LlmAgent` configuration.

Yes. The agent calls `get_user_profile` to pull individual records. You can feed this data into Gemini to generate personalized messaging strategies.

Your agent can pull the full directory with `list_flows` and get granular details via `get_flow`. It also has access to `list_mobile_experiences` for mobile app tours.

Use the `track_user_activity` tool. Your agent formats the event data as JSON and sends it over. This is perfect for logging actions that happen outside your frontend application.

Every connection requires a single endpoint token and executes within a secure V8 isolate. When your agent pushes payloads via `track_user_activity`, the transaction happens in memory and vanishes immediately. We retain zero logs of your custom events or profile updates.

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