Amplitude MCP. Analyze user behavior and revenue metrics directly in chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Amplitude MCP Server. Query behavioral data and product analytics directly from your AI client. Get user activity streams, calculate day-over-day retention, map conversion funnels, and pull daily revenue metrics without building dashboards.
What your AI agents can do
Active users
Gets the count of daily, weekly, or monthly active users (DAU/WAU/MAU) for a given date range.
Event segmentation
Queries and analyzes event segmentation based on a specific event name and date range.
Export events
Exports the raw stream of all Amplitude events that occurred within a specified date range.
Retrieves the full sequence of events for a specific user ID, helping you diagnose a user's exact journey.
Maps multi-step funnels, telling you which specific transition between events causes the most user loss.
Generates retention curves, quantifying how many users return to the product after a specific period.
Lists and analyzes behavioral cohorts, grouping users based on shared actions or characteristics.
Pulls immediate metrics like DAU/WAU/MAU and total daily revenue based on specified date ranges.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Amplitude MCP Server: 10 Tools for Behavioral Metrics
These tools allow your AI client to calculate active users, segment events, export raw data, and analyze complex user journeys directly from Amplitude.
019d754eactive users
Gets the count of daily, weekly, or monthly active users (DAU/WAU/MAU) for a given date range.
019d754eevent segmentation
Queries and analyzes event segmentation based on a specific event name and date range.
019d754eexport events
Exports the raw stream of all Amplitude events that occurred within a specified date range.
019d754eget cohort
Requests a download of a behavioral cohort group defined by user actions.
019d754eget funnel
Calculates the conversion rate across a series of defined steps (events) over a specified time period.
019d754eget retention
Calculates day-over-day retention rates between two specified events for a given time range.
019d754eget user activity
Retrieves the detailed, chronological activity stream for a single user based on their ID or email.
019d754elist cohorts
Lists all predefined behavioral cohorts and provides details on their membership size.
019d754erevenue analysis
Retrieves the total revenue generated daily by analyzing event data within a specified date range.
019d754esearch users
Searches for specific users using identifiers like user ID, device ID, or email address.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Amplitude, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You'll query behavioral data and product analytics straight from your AI client. Amplitude lets you pull user activity streams, map conversion funnels, and get daily revenue metrics without building a single dashboard.
get_user_activity retrieves the full sequence of events for a single user, letting you trace their exact journey by providing their ID or email. search_users helps you find specific users using identifiers like user ID, device ID, or email address. get_funnel calculates the conversion rate across multiple defined steps (events) over a set time period, pinpointing where users drop off. get_retention calculates day-over-day retention rates between two specified events for a given time range, measuring how many users stick around. event_segmentation queries and analyzes event segmentation based on a specific event name and date range. active_users gets the count of daily, weekly, or monthly active users (DAU/WAU/MAU) for a specified date range. revenue_analysis pulls the total revenue generated daily by analyzing event data within a set date range. list_cohorts lists all predefined behavioral cohorts and gives you details on their membership size. get_cohort requests a download of a behavioral cohort group defined by user actions. export_events exports the raw stream of all Amplitude events that occurred within a specified date range.
How Amplitude MCP Works
- 1 Subscribe to the server and input your Amplitude Project API Key and Secret Key.
- 2 Ask your agent a product analytics question (e.g., 'What was the conversion from X to Y last month?').
- 3 The agent executes the required tool calls, processes the data, and delivers the answer directly in the chat.
The bottom line is you get real-time product metrics answers without writing a single query or building a dashboard.
Who Is Amplitude MCP For?
Product Managers who need to test hypotheses fast. Data Analysts who get bogged down in manual reporting. Growth Teams needing instant visibility into revenue and active users. This is for anyone who needs to know why users behave the way they do, without writing complex SQL.
Tests new feature hypotheses by asking, 'Did users who viewed X actually complete Y?' or checking feature retention rates.
Cross-references raw event data, lists behavioral cohorts, and exports raw event streams for deeper, custom analysis.
Monitors daily revenue and active user counts instantly to track campaign performance and overall growth health.
Debugs specific user accounts by pulling the exact event activity stream for a problematic session.
What Changes When You Connect
- See the full user journey for any account using
get_user_activity. You don't have to guess why a user dropped off; you see the exact sequence of events that happened. - Pinpoint conversion leaks with
get_funnel. Instead of looking at a general drop-off percentage, you know precisely which step (e.g., 'Payment_Page_View') causes the biggest bottleneck. - Measure product stickiness over time using
get_retention. You get day-over-day curves showing exactly how many users come back after Week 1 or Month 3. - Identify high-value user groups by running
list_cohortsandget_cohort. This lets you stop targeting everyone and focus only on the most profitable user segments. - Instantly track operational health. Use
active_usersto see DAU/WAU/MAU changes, andrevenue_analysisto tie that activity directly to money. - Export raw data easily. Need to model something complex in Python? Use
export_eventsto get all raw data for a time range, bypassing the need for manual API calls.
Real-World Use Cases
A feature launch is underperforming.
The PM sees low adoption. They ask the agent: 'What was the conversion from 'Feature_View' to 'Feature_Use' last week?'. The agent uses get_funnel to show the exact drop-off rate, allowing the team to fix the flow instead of guessing.
A critical user account fails mid-transaction.
The CS rep needs to debug. They ask the agent to run get_user_activity for the user's email. The agent returns the full event stream, showing the user hit an 'API_Error' event right after 'Payment_Initiated', solving the issue immediately.
The marketing team needs to calculate LTV by segment.
The GM asks for the top segments. The agent runs list_cohorts to find the 'Premium Trial' cohort, and then uses revenue_analysis to calculate the average revenue generated by that specific group.
Investigating sudden drops in user counts.
The data analyst notices a dip in DAU. They ask the agent to compare active_users month-over-month and use export_events for the problematic period. This lets them cross-reference the dip with known external events.
The Tradeoffs
Trying to guess user paths
Assuming all users who view the pricing page must convert. You build a dashboard showing only the 'Viewed Pricing' -> 'Signed Up' flow, ignoring other activities.
→
Use get_funnel for the primary path, but then run get_user_activity on the users who dropped off. This reveals why they left, not just that they left.
Analyzing totals without segments
Looking at the overall DAU count and thinking that number represents the health of the product, ignoring that 90% of those users are just viewing the homepage.
→
First, use list_cohorts to identify the most valuable cohort (e.g., 'API Integrators'). Then, use revenue_analysis to see how that specific, high-value segment contributes to total revenue.
Sticking to one metric
Only checking get_retention to see if users come back, but failing to check if the revenue they bring back is worth the effort.
→
Always pair get_retention with revenue_analysis. This shows if users are returning, and if so, what value they bring back to the business.
When It Fits, When It Doesn't
Use this server if you need to answer specific, quantitative questions about user behavior and product performance. For example, 'How many users dropped off between Step A and Step B?' or 'What was the revenue from our top 10% cohort?'
Don't use this if you need to know why a user felt frustrated (that requires qualitative feedback). Also, don't use this if your goal is simply to monitor live, real-time system health (use dedicated monitoring tools for that). If you only want a general, high-level trend without specific dates or events, you're probably better off using a dedicated BI dashboard tool, not the raw data endpoint.
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
The old way of checking product health is a nightmare of tabs and filters.
Today, checking user flow means jumping between the core analytics dashboard, the raw event log, and the retention graph. You spend 30 minutes clicking through date ranges, applying filters, and copy-pasting numbers just to answer one question: 'Where are our users leaving?'
With this MCP server, you just ask the agent: 'Show me the conversion funnel from sign-up to first purchase.' You get the complete, filtered answer in a chat message. Done.
Amplitude MCP Server: Get the data, not the dashboard.
You never have to manually pull DAU counts or export raw events again. The agent handles the date formatting and the massive data joins for you, pulling the specific metrics you need right into your workflow.
It changes the process from 'Build a report to get an answer' to 'Ask a question and get the data.' That's the difference.
Common Questions About Amplitude MCP
How do I use the get_funnel tool to check conversion rates? +
You pass the comma-separated event names and the start/end dates. The agent returns the step-by-step conversion rate, showing you the conversion rate between each stage.
Can I use get_user_activity to debug a specific user? +
Yes. You provide the user's ID or email, and the agent returns the full, chronological event stream for that single user session, perfect for debugging.
How do I get daily revenue analysis with revenue_analysis? +
You specify the start and end dates (YYYYMMDD). The agent returns the total revenue generated for each day within that period.
Is get_retention the right tool for measuring user stickiness? +
Yes. get_retention measures how many users who performed an initial action (start_event) return to perform a later action (return_event) over time.
What is the difference between list_cohorts and get_cohort? +
list_cohorts just lists the names and sizes of behavioral groups. get_cohort requires a name and downloads the actual raw data for that specific group.
How do I use the export_events tool to get raw data for a specific time period? +
You pass the start and end dates in YYYYMMDDTHH format. This exports all raw event data for that window, allowing you to analyze granular details not covered by specific metrics.
What if I need to check multiple cohorts? Can I use list_cohorts first? +
Yes, running list_cohorts shows you all available behavioral cohorts. Then, you can use get_cohort for the specific group you want to analyze, which often requires polling until the data is ready.
Can I combine search_users with other tools, like get_user_activity, for a deep dive? +
Absolutely. You first run search_users to find the ID or email. Then, you pass that identifier to get_user_activity to pull the specific event stream for that user.
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.
Multi-server workflows that include Amplitude MCP
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
OneSignal
Automate push notifications via OneSignal — send messages, manage segments, and track delivery stats directly from any AI agent.
Instagram (Social Media & Business)
Manage your Instagram presence via AI — publish photos and reels, analyze insights, and manage comments.
Segment
Equip your AI agent with read access to your Segment workspace to audit sources, destinations, warehouses, and tracking plans natively.
You might also like
Privy
Manage users and wallets via Privy — create users, search profiles, and manage embedded wallets directly from any AI agent.
Cody AI
Enable your AI agent to manage knowledge-base bots, import documents, and query trained AI assistants via the Cody AI API.
GoBolt
Manage shipping rates, track parcel deliveries, and oversee logistics via AI agents with GoBolt.