How to Use the Amplitude MCP in Google ADK

Q: How do I configure the Amplitude MCP Server in Google ADK?

Run pip install google-adk to get the framework. Create an McpToolset using StreamableHttpServerParameters with your Vinkius URL. Inject that toolset into the tools array of your LlmAgent.

Q: How do I list Amplitude behavioral cohorts using Google ADK?

Your agent executes the listcohorts tool to see how users are grouped by behavior. If you need the actual user lists, it calls getcohort and polls the backend until the download is ready.

Q: Does the Google ADK integration support revenue tracking?

Yes. The revenueanalysis tool calculates daily income metrics based on your requested date range. Agents can pull this financial data to compare against marketing spend stored in Google Cloud.

Give Google ADK agents direct access to Amplitude so they can pull funnels, segment users, and export events into Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amplitude MCP to Google ADK

Create your Vinkius account to connect Amplitude 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 Amplitude with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Segment Product Events in Google ADK

Calling the `event_segmentation` tool splits your Amplitude product data by specific event names and date ranges. Your Gemini model uses its massive 1M+ token context window to digest months of user behavior trends at once. The agent maps out exactly which features get traction and which get ignored. Finding top-level metrics takes just one call to the `active_users` tool. The agent grabs daily, weekly, or monthly active user counts by passing YYYYMMDD date strings. Bringing this MCP Server output into Google Cloud lets you cross-reference product engagement with your existing BigQuery datasets.

Map Individual User Activity

The `search_users` tool locates specific accounts using an email, user ID, or device ID. Your Google ADK setup can pass these IDs directly into your enterprise pipeline. Restricting exposed tools via the `tool_names` filter keeps your agent focused purely on user discovery if needed. Once you have a target, the `get_user_activity` tool pulls their exact click path. Gemini processes this granular event stream to diagnose why a specific enterprise customer churned. You see every action they took before abandoning the platform.

Analyze Conversion Funnels

Triggering `get_funnel` measures how many users survive a sequence of comma-separated events. Your agent defines the start and end dates to build the conversion report. This raw drop-off data feeds perfectly into Vertex AI for deeper predictive modeling. Checking long-term loyalty relies on the `get_retention` tool. The agent defines a start acquisition event and a subsequent return event to see who comes back. Connecting this MCP integration to your Gemini framework turns static retention tables into conversational insights.

Setup guide

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

Run `pip install google-adk` to get the framework. Create an `McpToolset` using `StreamableHttpServerParameters` with your Vinkius URL. Inject that toolset into the `tools` array of your `LlmAgent`.

Gemini's massive context window is built exactly for this. The `export_events` tool pulls raw event data for a given YYYYMMDDTHH block. Your agent can read the entire dump without losing track of the earlier records.

Your agent executes the `list_cohorts` tool to see how users are grouped by behavior. If you need the actual user lists, it calls `get_cohort` and polls the backend until the download is ready.

Yes. The `revenue_analysis` tool calculates daily income metrics based on your requested date range. Agents can pull this financial data to compare against marketing spend stored in Google Cloud.

The server processes granular click streams and session durations. Vinkius runs the connection through a zero-trust architecture where no inbound ports are open. Your endpoint token authenticates the request without exposing your core infrastructure to the public internet.

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