Can my AI agent debug a specific user dropping out of our onboarding?

Yes. Search for the user by their email or ID using `search_users`, completely avoiding the manual lookup. Then, ask your agent to pull their raw activity stream via `get_user_activity`. The agent will retrieve all events triggered by this user, making it simple to spot exactly where they failed or stopped interacting.

Can I request funnel conversions without building a dashboard manually?

Absolutely. You can provide a sequence of events (e.g., 'Homepage Viewed', 'Sign Up Clicked', 'Account Created') and ask for the funnel conversion for the last 7 days. Your AI agent queries Amplitude and parses the exact drop-off rates at each step right into your prompt window.

How does the cohort fetching work for custom targeted segments?

Your agent can list all available cohorts associated with your project. Once you find the target cohort's ID, you can use the `get_cohort` tool to request its download URL. This is incredibly useful for instantly moving targeted lists of power-users or churned-users into your other workflows.

Amplitude MCP Server for Google ADK 10 tools — connect in under 2 minutes

Name: Amplitude
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 10 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Amplitude as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="amplitude_agent",
    instruction=(
        "You help users interact with Amplitude "
        "using 10 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Amplitude MCP Server

Connect your Amplitude account to your AI agent and seamlessly query behavioral data and product analytics using natural language.

Google ADK natively supports Amplitude as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 10 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

User Activity & Search — Search for specific users and track their detailed event stream to diagnose individual journeys
Funnels & Conversions — Request step-by-step conversion funnels to identify where users drop off
Retention — Generate day-over-day retention curves to understand how well features keep users engaged
Segmentation — Query event counts and uniques over time to see clear adoption trends
Cohorts — List your behavioral cohorts, view sizes, and request exports for further targeted analysis
Active Users & Revenue — Instantly pull DAU/WAU/MAU and daily revenue metrics right into your workflow

The Amplitude MCP Server exposes 10 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Amplitude to Google ADK via MCP

Follow these steps to integrate the Amplitude MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 10 tools from Amplitude via MCP

Why Use Google ADK with the Amplitude MCP Server

Google ADK provides unique advantages when paired with Amplitude through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Amplitude

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine Amplitude tools with BigQuery, Vertex AI, and Cloud Functions

Amplitude + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Amplitude MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Amplitude and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Amplitude tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Amplitude regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Amplitude

Amplitude MCP Tools for Google ADK (10)

These 10 tools become available when you connect Amplitude to Google ADK via MCP:

active_users

Start/End as YYYYMMDD. Get Amplitude daily/weekly/monthly active users (DAU/WAU/MAU)

event_segmentation

Pass event name, start/end as YYYYMMDD. Query Amplitude event segmentation

export_events

Amplitude is a product analytics platform. Pass start/end as YYYYMMDDTHH (e.g. 2026010100). Export raw Amplitude event data for a time range

get_cohort

Depending on the backend this may require polling until ready. Request an Amplitude cohort download

get_funnel

Pass comma-separated event names, start/end as YYYYMMDD. Query Amplitude funnel conversion

get_retention

Pass start_event (acquisition), return_event, start/end dates. Start/End should be YYYYMMDD. Query Amplitude retention

get_user_activity

Useful for diagnosing individual user journeys. Get Amplitude user activity stream

list_cohorts

Cohorts group users by behavior. List Amplitude behavioral cohorts

revenue_analysis

Start/End as YYYYMMDD. Get Amplitude revenue analysis by day

search_users

Useful to find specific users before checking their activity. Search Amplitude users by user ID, device ID, or email

Example Prompts for Amplitude in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Amplitude immediately.

"What's our funnel conversion from 'Landing_Page_View' to 'Sign_Up_Success' for the last 3 days?"

"Show the recent user activity for customer email@example.com"

"What is our Daily Active Users (DAU) count since start of the month?"

Troubleshooting Amplitude MCP Server with Google ADK

Common issues when connecting Amplitude to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Amplitude + Google ADK FAQ

Common questions about integrating Amplitude MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.