Countly Connector for AI agents.
8 live capabilities
Query product analytics and monitor user behavior in your app.
Waiting for input…
Why people use Countly
Countly for Product Analytics and User Behavior Tracking
This Connector changes that. You just ask your agent for the data you need. It pulls the numbers from Countly and puts them right in front of you, letting you spend your time on strategy instead of clicking through filters.
What Vinkius changes
You get instant access to your product's behavioral data through a natural chat interface.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Finding a funnel bottleneck
A product manager asks the agent to find where users drop off.
- Real-world use case 02
Bulk updating user profiles
A growth lead needs to update emails for a new cohort.
- Real-world use case 03
Quick KPI checks
An analyst needs to know the session count for the last hour.
Complete set · 8capabilities
The complete Countly capability set.
These are the exact actions your AI can choose when you ask it to work with Countly.
01—04
4 capabilities in this set.
Part of 8 available through Countly.
- 01 Capability
End session
Close out a user's current session. This ensures your engagement metrics stay accurate.
- 02 Capability
Read drill
Perform complex filtering and deep-dive analysis on your enterprise data. It handles the heavy lifting of segmentation.
- 03 Capability
Read events
Fetch detailed records for specific custom keys. Use this to see exactly what happened during a specific action.
- 04 Capability
Read metrics
Get standard numbers for sessions, users, or countries. This is the fastest way to see high-level app health.
05—08
4 capabilities in this set.
Part of 8 available through Countly.
- 05 Capability
Record events
Log specific actions taken by users inside your app. Use this to capture custom interactions like button clicks.
- 06 Capability
Update session
Extend the duration of an existing user session. It helps you keep track of long-running engagement.
- 07 Capability
Update user details
Change names, emails, or custom properties for a specific user. This keeps your user database clean and current.
- 08 Capability
Begin session
Start a brand new session for a user. Use this to initialize tracking for a new interaction.
Set up in minutes
One URL. Then ask Countly to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Countly from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_XCn8RC0rHZifc5Dr5D6YChNJVMfaKxEkqpKm6o4D/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Countly, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Countly for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_XCn8RC0rHZifc5Dr5D6YChNJVMfaKxEkqpKm6o4D/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Countly URL.
- Step 03
Save and start
Save the connection and enable Countly in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"countly": {
"url": "https://edge.vinkius.com/vk_preview_XCn8RC0rHZifc5Dr5D6YChNJVMfaKxEkqpKm6o4D/mcp"
}
}
} - Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Countly
Open Agent mode in chat and ask: "Using Countly, help me...". 8 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"countly": {
"url": "https://edge.vinkius.com/vk_preview_XCn8RC0rHZifc5Dr5D6YChNJVMfaKxEkqpKm6o4D/mcp"
}
}
} - Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Countly
Ask Copilot: "Using Countly, help me...". 8 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"countly": {
"url": "https://edge.vinkius.com/vk_preview_XCn8RC0rHZifc5Dr5D6YChNJVMfaKxEkqpKm6o4D/mcp"
}
}
} - Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Countly
Open Cascade and ask: "Using Countly, help me...". 8 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"countly": {
"url": "https://edge.vinkius.com/vk_preview_XCn8RC0rHZifc5Dr5D6YChNJVMfaKxEkqpKm6o4D/mcp"
}
}
} - Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Countly
Ask Cline: "Using Countly, help me...". 8 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add countly --transport http "https://edge.vinkius.com/vk_preview_XCn8RC0rHZifc5Dr5D6YChNJVMfaKxEkqpKm6o4D/mcp" - Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Countly
Ask Claude: "Using Countly, show me...". 8 tools are ready
Where the request belongs
Work Countly can move forward.
This is for the product person who is tired of switching tabs to find a single number. It solves the friction of manual data retrieval for teams who need to act on user behavior in real-time.
Product Manager
Checks feature adoption rates and KPI trends during standups without opening a browser.
Data Analyst
Runs quick segmentations and audits on specific event keys to answer ad-hoc questions.
Growth Marketer
Tracks conversion events and updates user profile properties to refine marketing funnels.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsAmplitude
Track user behavior, analyze product metrics, and manage cohorts directly from your AI agent using Amplitude's powerful analytics suite.
PostHog
Analyze product data via PostHog. list insights, track persons, inspect feature flags, and monitor experiments directly from any AI agent.
GrowingIO
Leading product analytics platform in China. manage events, segments, and metrics via AI.
Matomo
Open-source web analytics via Matomo. track visits, goals, and user behavior directly from any AI agent.
Mixpanel (Event Analytics & Insights)
Manage product analytics via Mixpanel. query event trends, track conversion funnels, and audit user cohorts.
Heap
Automate product analytics via Heap. track events, identify users, and manage segments directly from any AI agent.
Bring your own AI
Change the model, client or framework. Keep Countly connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Countly.
The practical details behind the request, access and result.
How does the Countly MCP help my product team?
It lets your team talk to your analytics data using natural language. Instead of digging through dashboards, you can ask your agent for specific metrics, user counts, or event data instantly.
Can I use Countly MCP to update user information?
Yes. Your agent can update names, emails, and custom properties for specific users directly through the Connector, which helps keep your user database current without manual entry.
Does Countly MCP support custom events?
It does. You can have your agent record specific actions within your app, like button clicks or purchases, and then query those events later to see how users are interacting with your features.
Is Countly MCP good for large scale data filtering?
If you have the Enterprise Edition, it includes the Drill API. This allows your agent to perform complex segmentations and deep-dive analysis into your data.
Can I use Countly MCP with Claude or Cursor?
Yes. This Connector is compatible with any MCP-supported client, including Claude, Cursor, Windsurf, and VS Code, allowing you to access your analytics from your favorite workspace.
What happens when I ask for metrics via Countly MCP?
Your agent will pull the latest data for sessions, users, or countries and present it to you in a clear, readable format, often including summaries or tables.
How can I retrieve aggregated data like total sessions or user counts?
You can use the read_metrics capability. 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 capability. 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 capability to perform complex queries and segmentation using the Drill API.
One connection away
Give your agent a direct line to Countly.
Connect Countly once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available