How to Use the Kissmetrics MCP in Claude Code

Q: How do I add Kissmetrics to Claude Code?

Run claude mcp add --transport http kissmetrics -- in your terminal. Make sure all flags come before the server name. Use claude mcp list to verify the connection.

Q: Can Claude Code trigger Kissmetrics events from a shell script?

Yes. You can prompt the CLI to execute recordevent based on local file changes or cron triggers. It acts as a headless bridge to your analytics account.

Q: Why use Claude Code for Kissmetrics instead of the web UI?

Terminal users need data where they work. Pulling querypeoplecount directly into your SSH session saves you from opening a browser during a deployment. It keeps your workflow entirely text-based.

Q: Can I automate Kissmetrics identity merging with Claude Code?

You can write a script that feeds user pairs into the aliasidentities tool. The CLI reads your database dump and maps the anonymous IDs to known emails in bulk.

Pipe Kissmetrics analytics directly into your terminal with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kissmetrics MCP to Claude Code

Create your Vinkius account to connect Kissmetrics 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 Kissmetrics with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Script headless tracking pipelines

The `record_event` tool lets Claude Code push server-side behavior logs directly from your command line using this MCP server. You can wire this into a post-deploy bash script to track release metrics automatically. The CLI formats the identity payload and fires the request without any graphical interface. You can chain this with `set_person_properties` to update user states during a database migration. Your agent reads a CSV of user IDs, loops through them, and updates the Kissmetrics profiles. The entire operation runs headless in your terminal.

Monitor the Kissmetrics MCP Server from the CLI

Running `query_metric_data` allows your terminal agent to fetch live conversion stats during an incident. If you suspect a release broke the checkout flow, Claude Code pulls the historical metric ID and compares it to the last hour. You get immediate operational context. The agent follows up by executing `query_people_count` to see exactly how many accounts hit the error state. You pipe that output directly into a Slack notification script. Your incident response gets backed by hard product data instantly.

Audit tracking schemas in CI/CD

Triggering `list_event_types` lets Claude Code validate your event dictionary during a GitHub Action. The agent pulls the live schema and compares it against the tracking calls in your pull request. It fails the build if a developer tries to introduce an undocumented event name. It performs the same check using `list_property_names` to enforce payload consistency. You stop bad data from polluting your analytics before the code ever merges. The CLI handles the validation step entirely in the background.

Setup guide

Set up Kissmetrics 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 kissmetrics-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http kissmetrics-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 Kissmetrics 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": {
    "kissmetrics-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 Kissmetrics. 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 Kissmetrics 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 Kissmetrics MCP in Claude Code

Run `claude mcp add --transport http kissmetrics -- ` in your terminal. Make sure all flags come before the server name. Use `claude mcp list` to verify the connection.

Yes. You can prompt the CLI to execute `record_event` based on local file changes or cron triggers. It acts as a headless bridge to your analytics account.

Terminal users need data where they work. Pulling `query_people_count` directly into your SSH session saves you from opening a browser during a deployment. It keeps your workflow entirely text-based.

You can write a script that feeds user pairs into the `alias_identities` tool. The CLI reads your database dump and maps the anonymous IDs to known emails in bulk.

This integration touches raw email addresses and granular behavioral logs. Claude Code processes these properties locally in your shell environment. The terminal history is the only place the `set_person_properties` payload touches disk.

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