How to Use the GrowingIO MCP in Claude

Q: How do I connect my local GrowingIO metrics to Claude Desktop?

Open your claudedesktopconfig.json file and add the GrowingIO server configuration under the mcpServers block. Restart the app, and you will see the hammer icon indicating the 10 custom tools are active.

Q: What happens when I request a large user segment?

The getsegmentusers tool fetches the user list in batches. Your agent processes the payload locally, ensuring the desktop app does not freeze during large data transfers.

Query GrowingIO funnel analytics and user segments directly inside Claude Desktop to inspect conversion drops on the fly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GrowingIO MCP to Claude Desktop

Create your Vinkius account to connect GrowingIO to Claude Desktop 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 GrowingIO with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inspect Funnel Drops and Event Data

This MCP Server exposes the `get_funnel` and `get_event` tools directly to your Claude Desktop chat, letting you pull real-time conversion metrics without opening the web UI. You ask your agent to analyze a drop-off, and it immediately retrieves the exact steps and raw event definitions. No more manual exports or SQL queries just to check a product metric. Your agent uses the `list_events` tool to map the customer journey, matching user behaviors to specific tracking variables in your local environment.

Segment Users Directly in Your Workspace

The `get_segment_users` tool lets you pull active user IDs from specific cohorts into Claude Desktop. You can immediately feed this list into your local script or ask your agent to draft a targeted email campaign based on actual behavioral data. Running this MCP server locally means your data stays private. Your agent calls `list_segments` to find the exact cohort you need, then parses the user list without sending raw customer profiles to external servers.

Audit Your Tracking Setup with Claude Desktop

Debugging your tracking schema happens instantly when you connect the `list_variables` and `list_log_sources` tools to your agent. You don't have to guess if a custom parameter is active. Your agent queries your GrowingIO project metadata using `get_project_info` to verify active SDK sources. If a variable is missing, you'll know exactly which data stream is broken before you write any code.

Setup guide

Set up GrowingIO MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The GrowingIO MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the GrowingIO MCP configuration

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

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under growingio-mcp.

json

{
  "mcpServers": {
    "growingio-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 GrowingIO. 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 GrowingIO 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 GrowingIO MCP in Claude Desktop

Open your `claude_desktop_config.json` file and add the GrowingIO server configuration under the `mcpServers` block. Restart the app, and you will see the hammer icon indicating the 10 custom tools are active.

Yes, this MCP setup works on Claude Web by adding the remote server URL in your integration settings. This lets you query user segments and conversion funnels from any browser.

The desktop agent passes your API credentials directly to the GrowingIO endpoints. If you exceed your plan limits while running `get_metrics`, the server returns a standard rate-limit error which the agent displays in chat.

The `get_segment_users` tool fetches the user list in batches. Your agent processes the payload locally, ensuring the desktop app does not freeze during large data transfers.

No. The MCP connection runs as a local subprocess on your machine, which means your tracking variables and event metadata never touch third-party servers. Your API tokens remain encrypted on your local drive.

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