How to Use the Countly MCP in Claude Code

Q: How do I pipe Countly event logs to other CLI tools using Claude Code?

You can have Claude Code call readevents and then pipe the resulting Countly event JSON directly into local terminal utilities like jq or custom bash scripts.

Q: Can I run automated Countly session tests in a CI/CD pipeline with Claude Code?

Yes, you can run Claude Code headlessly to trigger beginsession and endsession sequences to mock Countly sessions during your automated deployment tests.

Run headless Countly analytics audits and trigger custom event tracks directly from your Claude Code terminal.

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 Claude Code

Create your Vinkius account to connect Countly to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless session testing in Claude Code

This Countly MCP Server exposes `begin_session`, `update_session`, and `end_session` directly to your terminal environment. You can pipe these tools into shell scripts via Claude Code to simulate user traffic, verify session timeouts, or test telemetry collection during CI/CD runs. It removes the need for any graphical interface. Because Claude Code operates entirely in the terminal, you can easily script Countly session lifecycles without opening a browser or booting up a heavy IDE.

Command-line event recording and validation

The integration uses `record_events` and `read_events` to let you track and verify custom application behavior straight from the Claude Code command line. When debugging a production issue, you can tell your agent to query the latest custom events to see if a specific error code was logged in Countly. It gives you instant diagnostics. You can pipe the JSON output of these Countly event tools directly into utilities like jq or grep, making terminal-based analytics troubleshooting incredibly fast with Claude Code.

Instant metrics extraction via MCP Server

This server provides `read_metrics` and `read_drill` to pull raw behavioral cohorts and standard usage metrics right into your Claude Code shell. If you need a quick count of daily active users, you ask your agent, and it queries your Countly instance to return a formatted text table. It replaces slow dashboard loading times. You can also update user segments using `update_user_details` to quickly flag internal test accounts. Running this command directly from your terminal session updates metadata instantly.

Setup guide

Set up Countly MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see countly-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Countly transactions." It will automatically discover and invoke the available Countly tools.

Terminal

claude mcp add --transport http countly-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "countly-mcp": {
      "type": "url",
      "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 Claude Code

You can have Claude Code call `read_events` and then pipe the resulting Countly event JSON directly into local terminal utilities like jq or custom bash scripts.

Yes, you can run Claude Code headlessly to trigger `begin_session` and `end_session` sequences to mock Countly sessions during your automated deployment tests.

You add the MCP server to your local Claude Code config using the command-line interface, passing your Countly credentials as environment variables or command flags.

Yes. If you use Countly Enterprise, Claude Code can execute `read_drill` to pull complex behavioral cohorts directly into your terminal output.

Your Countly analytics credentials and user session data are stored locally in your terminal's encrypted configuration. The MCP connection uses transport-level security, ensuring no telemetry is cached or intercepted.

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