4,500+ servers built on MCP Fusion
Vinkius
GoatCounter logo
Vinkius
Claude Code logo

How to Use the GoatCounter MCP in Claude Code

Manage your GoatCounter analytics and fetch site traffic directly from your terminal using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

GoatCounter MCP on Cursor AI Code Editor MCP Client GoatCounter MCP on Claude Desktop App MCP Integration GoatCounter MCP on OpenAI Agents SDK MCP Compatible GoatCounter MCP on Visual Studio Code MCP Extension Client GoatCounter MCP on GitHub Copilot AI Agent MCP Integration GoatCounter MCP on Google Gemini AI MCP Integration GoatCounter MCP on Lovable AI Development MCP Client GoatCounter MCP on Mistral AI Agents MCP Compatible GoatCounter MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Claude Code

Connect GoatCounter MCP to Claude Code

Create your Vinkius account to connect GoatCounter 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

Query site metrics directly from your command line

Keep your hands on the keyboard by fetching GoatCounter traffic stats without opening a web browser. Claude Code uses `get_stats_total` to pull your total pageview counts for any date range you specify in your terminal. For quick terminal reports, this CLI tool calls `get_stats_hits` to list your most popular GoatCounter paths. You can pipe this output directly into other command-line utilities for instant terminal-based analysis.

Run automated analytics exports via the Claude Code CLI

Backing up your analytics data shouldn't require manual clicks. This MCP Server allows Claude Code to trigger background GoatCounter exports using `start_export` and monitor their progress with `get_export` directly from your shell. Once the export is ready, Claude Code downloads the raw file via `download_export`. This makes it simple to integrate raw GoatCounter data archiving directly into your terminal-based cron jobs or shell script pipelines.

Inspect site configurations and user accounts

Check your GoatCounter subscription limits and current API key permissions directly from your terminal. This MCP configuration lets Claude Code use `get_me` to verify your account details and `list_sites` to show all accessible domains. If you need to verify a specific tracker configuration, Claude Code calls `get_site` to print the settings. You get a fast, text-based overview of your GoatCounter analytics endpoints without leaving your command line.

Setup guide

Set up GoatCounter 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. 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. 2

    Verify the connection

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

  3. 3

    Start using tools

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

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

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

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 GoatCounter MCP in Claude Code

Run the command `claude mcp add --transport http goatcounter -- ` in your terminal. Make sure all configuration flags come before the server name.
Yes. You can ask the CLI tool to send a test event, and it will use `count_hits` to verify that your tracking endpoint is active and accepting data.
Just ask the tool to check a specific URL. It will call `get_stats_hits_path` to pull the referral sources and display them directly in your terminal window.
You can update any site settings by telling the agent what to change. It will execute `update_site` to apply the modifications immediately without needing a browser.
The CLI tool communicates with the API using your locally stored API key. Your site settings and total pageview counts are processed in memory and never sent to any external telemetry servers.

Start using the GoatCounter MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 14 tools

We've already built the connector for GoatCounter. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 14 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.