How to Use the Pirsch Analytics MCP in Claude Code

Q: How do I install the Pirsch Analytics server in Claude Code?

Run claude mcp add --transport http pirsch-analytics-mcp -- in your terminal. Make sure to place all flags before the server name. The config saves to /.claude.json.

Q: Can Claude Code and Pirsch Analytics run in a GitHub Action?

Yes. You can execute headless commands to fetch getstatisticsgoals during a build step. If conversions drop below a threshold, the pipeline fails automatically.

Q: How do I query UTM sources from the CLI?

Just ask the agent to check your campaign stats. It calls getstatisticsutmsource and prints the raw JSON or a formatted summary straight to standard output.

Manage your Pirsch Analytics MCP Server directly from your terminal with Claude Code to automate reporting and monitor live metrics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pirsch Analytics MCP to Claude Code

Create your Vinkius account to connect Pirsch Analytics to Claude Code — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pirsch Analytics with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Instant Infrastructure Audits

The `list_domains` tool lets your terminal agent audit every registered web property in seconds. Claude Code hits the API, formats the output into a clean CLI table, and pipes the results into your infrastructure logs. Need to spin up a new environment? You run a single command. The agent uses `create_domain` to register the site, grabs the new tracking tokens, and injects them straight into your `.env` files.

Headless Traffic Monitoring with Claude Code

The `get_statistics_overview` tool pulls hard numbers on your active visitors without a browser. You can schedule a cron job that triggers the agent to fetch yesterday's traffic and dump it into a Slack webhook. When a deployment goes out, you want immediate feedback. The agent loops `get_statistics_active` to watch real-time user counts drop or spike, giving you instant terminal alerts if a release breaks the site.

Batch Event Processing via MCP

The `send_event_batch` tool allows you to replay backend logs directly into your analytics provider. Claude Code parses your server access logs, formats the data, and pushes thousands of events in a single command. It handles the exact same process for page views using `send_hit_batch`. You get accurate historical data backfill without writing custom Python scripts or dealing with rate-limit backoff logic.

Setup guide

Set up Pirsch Analytics 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 pirsch-analytics-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http pirsch-analytics-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 Pirsch Analytics 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": {
    "pirsch-analytics-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 Pirsch Analytics. 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 Pirsch Analytics 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 Pirsch Analytics MCP in Claude Code

Run `claude mcp add --transport http pirsch-analytics-mcp -- ` in your terminal. Make sure to place all flags before the server name. The config saves to `~/.claude.json`.

Yes. You can execute headless commands to fetch `get_statistics_goals` during a build step. If conversions drop below a threshold, the pipeline fails automatically.

Just ask the agent to check your campaign stats. It calls `get_statistics_utm_source` and prints the raw JSON or a formatted summary straight to standard output.

It does. You can pipe a text file of user actions into the agent, and it will map them to the `send_event` endpoint.

This setup handles IP addresses and user-agent strings during hit tracking. Since the MCP connection is ephemeral and headless, your environment variables and traffic data disappear the moment the terminal session ends.

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