Countly MCP. Query user behavior and event metrics instantly.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Countly. Track user behavior and application performance directly from your AI agent. This server lets you start, stop, and update user sessions, record custom events with keys and counts, and pull deep behavioral metrics.
It's built to query user actions and build user profiles without leaving your chat window.
What your AI agents can do
Begin session
Starts a new user session record in Countly.
End session
Ends the current user session record.
Read drill
Runs advanced filtering to analyze specific data segments (Enterprise Edition).
Start, update, or end user sessions to measure how long users stay engaged with the app.
Record custom events, including keys and counts, to see exactly how users interact with specific features.
Update core user details—like email or name—to maintain accurate user profiles across your system.
Get aggregated data on sessions, total users, or geographical sources.
Retrieve specific data points for custom events you've logged, allowing targeted analysis.
Perform complex data segmentation and filtering using the Drill API for deep investigation.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
019e5d0dbegin session
Starts a new user session record in Countly.
019e5d0dend session
Ends the current user session record.
019e5d0dread drill
Runs advanced filtering to analyze specific data segments (Enterprise Edition).
019e5d0dread events
Retrieves data for specific custom events that were recorded.
019e5d0dread metrics
Pulls standard aggregated metrics like total sessions, users, or countries.
019e5d0drecord events
Logs a specific action taken by a user within the application.
019e5d0dupdate session
Extends the duration of an existing user session.
019e5d0dupdate user details
Changes personal information or properties associated with a user's profile.
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 Countly, 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
Countly MCP Server - Track User Sessions & Events
Your AI agent lets you track user behavior and app performance directly from Countly. You can manage user sessions, log custom events, and pull detailed user metrics without leaving your chat window.
Track User Activity Cycles
begin_sessionstarts a new user session record.update_sessionextends the duration of an existing session.end_sessioncloses the current user session record.
Log Specific User Actions
record_eventslogs an action a user took in the app. This tool lets you include custom keys and counts with the event.update_user_detailschanges a user's profile data, like their email or name.
Querying User Data
read_metricspulls standard numbers like total sessions, total users, or the user's country.read_eventsgets data for specific custom events you logged, letting you analyze them directly.read_drillruns advanced filtering to analyze specific data segments (this is for Enterprise Edition).
How Countly MCP Works
- 1 Subscribe to the server and provide your Countly Server URL and API credentials (App Key, API Key, App ID).
- 2 Your AI client authenticates with the server, making the tools available for invocation.
- 3 You prompt your agent with a natural language request (e.g., 'What were the total sessions last week?'), and the agent uses the exposed tools to pull the data.
The bottom line is, you ask your agent a question in plain English, and it runs the necessary Countly tools to get the answer.
Who Is Countly MCP For?
Product Managers, Data Analysts, and Growth Teams. If your job involves figuring out why users aren't converting or what features people actually use, this is for you. It lets you skip the BI dashboard and ask the data questions directly in your chat.
Checks KPIs and feature adoption rates by asking for specific metrics or user segment data, instead of building a new dashboard.
Performs quick segmentations and audits of event logs using natural language queries to test hypotheses.
Tracks conversion events and updates user profiles to ensure marketing funnels are being optimized.
What Changes When You Connect
- See total sessions and average duration immediately using
read_metrics. You get key metrics—like total active users or top countries—without leaving your chat. - Track feature adoption rates by calling
read_events. You can ask for data on a specific custom event key, telling you exactly which features users are interacting with. - Understand the full user lifecycle by using
begin_session,update_session, andend_session. You maintain a clear record of engagement time and active status. - Maintain accurate user records by calling
update_user_details. This keeps your user profile—including name or email—synced with the latest data. - Deep-dive into problem areas using
read_drill. This tool lets you apply complex filters to pinpoint why a specific user segment is struggling. - Log critical user actions instantly with
record_events. You can record a 'purchase' event and attach a sum, confirming the data point right away.
Real-World Use Cases
Auditing a conversion funnel bottleneck
A Growth Marketer notices drop-off between signup and first purchase. They ask their agent to use read_events to pull all 'cart_abandon' events. The agent runs the tool and returns a count of the specific event, immediately showing the scale of the problem. They then use read_metrics to check user counts in that segment.
Investigating a slow-performing feature
A Product Manager suspects Feature X isn't used enough. They ask their agent to use read_events to filter for 'feature_x_view' and include the count. If the count is low, they then use read_drill to segment the data by country to see if the problem is regional.
Updating user data after an offline interaction
A Support Agent learns a user's correct email address during a call. Instead of logging into the dashboard, they ask their agent to call update_user_details with the user ID and the new email. The profile is instantly corrected in Countly.
Modeling a complex user journey
A Data Analyst wants to know the total engagement time for a specific group. They start by calling begin_session for the target user, then use update_session to simulate activity, and finally call end_session. They use read_metrics to get the final, aggregated session duration.
The Tradeoffs
Manual dashboard hopping
Having to switch between the main dashboard, the event log, and the user profile tab to gather a full picture of user activity.
→
Ask your agent to run read_metrics for total sessions, then use read_events for the specific action, and finally use update_user_details if the user record needs correcting. Keep it all in the chat.
Guessing event keys
Manually trying to figure out the right filter or custom key to find a specific user action, which requires deep knowledge of the Countly schema.
→
Use natural language with read_events. You just tell your agent the action—like 'purchases'—and it structures the query for you.
Ignoring session state
Running a query on user metrics without first defining the scope by calling begin_session. The data returned is incomplete or misleading.
→
Always start by calling begin_session for the user you care about. This sets the necessary context before you run any other read tools.
When It Fits, When It Doesn't
Use this server if your primary need is understanding why your product performs the way it does—tracking usage, segmenting users, or quantifying events. You need to know the behavior of the user base. Don't use this if you just need to pull static data (like a list of all users). For that, a simple database query tool is better. If you are building a complex, real-time behavioral graph, you need a specialized graph database, not this event-logging tool. This server excels at answering 'what happened' by logging and querying events and session states.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Countly. 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 8 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Tracking user activity shouldn't require jumping between five dashboards.
Today, figuring out if a new feature is sticky means logging into the analytics platform. You navigate to the 'Sessions' tab, then switch to 'Events' to check the keys. Next, you filter by the correct user segment, and finally, you copy a metric value into a spreadsheet. It takes five tabs and twenty minutes.
With this MCP server, you ask your agent directly: 'How many sessions tracked the 'checkout' event last month?' The agent runs the necessary tools, pulls the aggregated data, and gives you the number in the chat. No dashboard hops. Just the answer.
Countly MCP Server: Manage user sessions and events.
The manual steps that go away are the manual calls to the API to start/stop sessions, and the process of manually updating user details in a separate CRM. You don't have to switch context to update a user's name or extend their session time.
The difference is that you treat analytics and user data as a single, conversational resource. You manage the entire lifecycle—from session start to event logging—without ever leaving the conversation.
Common Questions About Countly MCP
How do I use the `read_metrics` tool with Countly MCP Server? +
To read metrics, ask your agent for the specific data you need, like 'total sessions for the last week.' The agent calls read_metrics and returns the aggregated number and time frame.
Can I use `read_events` to check for a specific purchase event? +
Yes. You tell your agent the event name and the timeframe. The agent runs read_events and gives you the detailed data points for that custom event.
How do I update user data using the `update_user_details` tool? +
You tell your agent which user ID needs updating and what the new information is (e.g., 'Update user 123's email to X'). The agent calls update_user_details and confirms the change.
Does `read_drill` allow complex filtering on user data? +
Yes. read_drill handles complex filtering. You just describe the segment you want—like 'users from Germany who viewed product Y'—and the agent runs the advanced query.
What do I need to do before using the `begin_session` tool? +
You must subscribe to the server and provide the Countly Server URL and API credentials. Your AI client then uses these credentials to start tracking user activity.
How do I manage session length with the `update_session` tool? +
The update_session tool extends the duration of an existing session. This is useful if you need to track a user's engagement past the default timeout period.
Is there a way to check for user actions with `record_events`? +
Yes, record_events records specific actions, allowing you to track custom keys, counts, and segmentation data for every user interaction in the app.
When should I use the `end_session` tool? +
You use end_session when the user's activity concludes. This ensures that the time spent in the application is accurately logged and counted.
How can I retrieve aggregated data like total sessions or user counts? +
You can use the read_metrics tool. Simply specify the method (e.g., 'sessions' or 'users') to get the aggregated analytics data from your Countly instance.
Can I record custom user actions with metadata? +
Yes! Use the record_events tool. You can provide a device ID and an array of event objects containing keys, counts, and segmentation details to track specific interactions.
Does this server support advanced filtering for Enterprise users? +
Yes, if you have the Enterprise Edition, you can use the read_drill tool to perform complex queries and segmentation using the Drill API.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
FantasyData (SportsDataIO)
Access real-time sports data via FantasyData (SportsDataIO) — track players, scores, and schedules for NFL, NBA, and MLB.
Blockscout
Explore Ethereum-based blockchains directly from your AI agent. Query addresses, tokens, transactions, and smart contracts via Blockscout's open-source API.
Deterministic EdTech Quiz Scorer
Transform your AI into a ruthless, high-precision EdTech examiner. Automatically cross-reference quiz answers against weighted keys to generate granular performance metrics instantly.
You might also like
Regulations.gov (eRulemaking)
Access US federal regulations, search documents, public comments, and dockets directly from agencies like the EPA and FAA.
Open Food Facts Alternative
Access the world's largest open food database — retrieve nutrition facts, ingredients, and environmental scores for millions of products.
8x8 Contact Center
Real-time contact center analytics — monitor queues, agent performance, and live metrics via AI.