How to Use the Pirsch Analytics MCP in Windsurf

Q: Can Windsurf and Pirsch Analytics track batch events?

Yes. The server includes sendhitbatch and sendeventbatch endpoints. Cascade can write the script to aggregate these events locally before pushing them to the API.

Q: How does Pirsch Analytics work with Windsurf to analyze traffic?

The agent runs getstatisticsvisitor to pull demographic data. It then formats that data into whatever chart or summary table you requested in the chat.

Q: What kind of domains can I manage here?

You can manage any web property. The listdomains and createdomain tools give your agent full CRUD access to your client sites directly from the command palette.

Connect Pirsch Analytics to Windsurf to autonomously track hits, pull privacy-first metrics, and manage domains.

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 Windsurf

Create your Vinkius account to connect Pirsch Analytics to Windsurf — 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Zero-Prompt Traffic Analysis

The `get_statistics_overview` tool feeds exact domain metrics straight into Windsurf. Cascade reads your current workspace context, decides which data points matter, and pulls active visitor counts alongside page statistics without you writing a single prompt. You set a goal to analyze recent traffic drops. The agent chains `get_statistics_referrer` and `get_statistics_utm_source` to map out the decline, then writes a markdown report right in your editor. No jumping between browser tabs.

Tracking Setup via the Windsurf MCP Server

The `send_event` and `send_hit` tools let your agent wire up analytics directly inside your codebase. Cascade scans your React components, identifies missing conversion triggers, and inserts the correct batch tracking functions like `send_event_batch` where they belong. It handles the boilerplate for you. If you need a new environment tested, it runs `create_domain` to spin up a fresh target, configures the tokens, and immediately pushes test hits to verify the connection.

Deep Event Inspection

The `get_statistics_events` tool exposes your custom interaction data to the IDE. Windsurf pulls this raw event data and cross-references it with your frontend code to spot dead buttons or broken forms. When conversion rates dip, Cascade grabs data using `get_statistics_goals` and `get_statistics_active`. It looks at the active user sessions, compares them against your defined goals, and suggests code edits to fix the funnel.

Setup guide

Set up Pirsch Analytics 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 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

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 Pirsch Analytics payment history." If connected, Cascade will call the Pirsch Analytics tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "pirsch-analytics-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 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 Windsurf

Open Settings, go to Cascade, and find the MCP Servers UI. You can add the server configuration directly to your `mcp_config.json` or use the built-in marketplace. Click refresh, and Cascade auto-discovers the 14 new tools.

Yes. The server includes `send_hit_batch` and `send_event_batch` endpoints. Cascade can write the script to aggregate these events locally before pushing them to the API.

The agent runs `get_statistics_visitor` to pull demographic data. It then formats that data into whatever chart or summary table you requested in the chat.

You can manage any web property. The `list_domains` and `create_domain` tools give your agent full CRUD access to your client sites directly from the command palette.

This integration touches raw hit and event payload data. The MCP protocol runs locally in a sandboxed V8 isolate, meaning your API tokens and visitor statistics never leak to third-party model trainers.

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