How to Use the Countly MCP in Windsurf

Q: How does Windsurf use the Countly MCP Server to automate telemetry testing?

Cascade hooks into tools like recordevents directly in Windsurf to send test telemetry and reads it back using readevents. You don't have to manually check the Countly dashboard to see if your new event triggered.

Q: Can Cascade chain multiple Countly queries in Windsurf without prompting me?

Yes, Cascade evaluates the output of readmetrics in Windsurf and immediately decides whether to call readdrill to pinpoint drop-off points. It runs the entire Countly diagnostic sequence in a single turn.

Q: What happens if a Countly session update fails during a Cascade run in Windsurf?

If updatesession returns an error, Cascade reads the failure payload inside Windsurf, stops the execution chain, and suggests a fix for your session tracking logic.

Q: How does this server handle the privacy of my Countly analytics data in Windsurf?

All user session data and behavioral metrics retrieved via readmetrics stay local to your Windsurf machine. The connection runs in a secure sandbox, meaning Vinkius handles the endpoint token without exposing your raw Countly event payloads to external networks.

Let Cascade chain Countly metrics queries and user session updates autonomously inside your Windsurf IDE.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Countly MCP to Windsurf

Create your Vinkius account to connect Countly to Windsurf and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Countly with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain session tracking directly in Windsurf

This Countly MCP Server lets Cascade automatically initiate and manage user tracking flows within your Windsurf workspace using `begin_session`, `update_session`, and `end_session`. When you ask Cascade to verify a Countly user journey, it doesn't wait for your permission at every step. It starts the session, updates the parameters as the user navigates, and terminates it once the test path completes. You get real-time validation of your Countly session logic without manually writing mock telemetry code inside Windsurf. Cascade watches the outputs of these session tools to confirm your analytics integration works before you push.

Multi-step event profiling with Cascade

The server exposes `record_events` and `read_events` to let Cascade write and retrieve custom telemetry directly from your Windsurf workspace. If you ask Cascade to debug why a specific Countly funnel step is failing, it queries your live events list and edits your tracking code. It works entirely in the background. Cascade doesn't just display the telemetry inside Windsurf. It analyzes the payload structure returned by the Countly event tools and adjusts your local application code to match what your production tracking expects.

Deep segmentation queries inside your IDE

This MCP integration uses `read_drill` and `read_metrics` to pull granular behavioral cohorts straight into your Windsurf editor. When you tell Cascade to optimize a feature for a specific Countly user segment, it fetches the exact cohort breakdown to guide its edits. You get precise behavioral data injected directly into your coding context. This means Cascade writes code based on actual Countly metrics, not guesswork. It updates user profiles via `update_user_details` to flag test accounts during your local Windsurf dry runs.

Setup guide

Set up Countly MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Countly MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Countly payment history." If connected, Cascade will call the Countly tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "countly-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Countly now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Countly MCP in Windsurf

Cascade hooks into tools like `record_events` directly in Windsurf to send test telemetry and reads it back using `read_events`. You don't have to manually check the Countly dashboard to see if your new event triggered.

Yes, Cascade evaluates the output of `read_metrics` in Windsurf and immediately decides whether to call `read_drill` to pinpoint drop-off points. It runs the entire Countly diagnostic sequence in a single turn.

No. You define your Countly API credentials once in your local Windsurf MCP configuration file, and Cascade handles the authenticated requests behind the scenes.

If `update_session` returns an error, Cascade reads the failure payload inside Windsurf, stops the execution chain, and suggests a fix for your session tracking logic.

All user session data and behavioral metrics retrieved via `read_metrics` stay local to your Windsurf machine. The connection runs in a secure sandbox, meaning Vinkius handles the endpoint token without exposing your raw Countly event payloads to external networks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript