Integrate Amplitude with Claude, Cursor, Chatbots & AI Agents MCP Server

Analyze product data via Amplitude — get user activity, calculate retention, analyze funnels, and track revenue directly from any AI agent.

GDPR Free for Subscribers

Compatible with every major AI agent and IDE

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

+ other MCP clients

active

Active users on Amplitude

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

event

Event segmentation on Amplitude

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

export

Export events on Amplitude

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

get

Get cohort on Amplitude

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

get

Get funnel on Amplitude

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

get

Get retention on Amplitude

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

get

Get user activity on Amplitude

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

list

List cohorts on Amplitude

Cohorts group users by behavior. List Amplitude behavioral cohorts

revenue

Revenue analysis on Amplitude

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

Search users on Amplitude

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

Security & Code Integrity Audit

Every tool in the Amplitude MCP Server is continuously audited by the Vinkius Security Engine. We guarantee zero-trust payload isolation, strict data boundaries, and deterministic execution for enterprise-grade AI agents.

A+Score: 100

How Vinkius protects your data

Can I set different limits for each virtual assistant on my team?

Absolutely. You have full control in our command center. You can create an AI agent that only "reads" data so the support team can answer questions, and another superpowered agent that can "edit" and "create" information exclusively for your operations team. Each AI gets exactly the level of access you allow.

What happens if the underlying API rate limits my agent?

Our edge infrastructure automatically handles backoffs, queueing, and throttling. If an AI agent sends too many erratic requests, Vinkius manages the rate limits gracefully, ensuring your backend doesn't crash.

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.

Does the AI train on my tools or API data?

No. Vinkius enforces a strict Zero-Retention policy. Your data simply passes through our secure servers to complete the requested action and is instantly forgotten. Nothing you do here is ever stored, logged, or used to train any artificial intelligence.

Amplitude Capabilities for AI Assistants

This integration supports direct MCP execution, enabling your chatbots to query and modify data within these specific environments.

AI-Driven user behavior Workflows

The Amplitude toolkit enables AI agents to execute user behavior commands. It handles protocol translation for growth engine integrations natively.

Scaling product analytics via MCP

Integrate the Amplitude server to handle product analytics requests natively. It provides the schemas required for ChatGPT and Cursor to manage growth engine data.