How to Use the GoatCounter MCP in LangChain

Q: How does the agent handle large data exports?

The agent triggers startexport to run the job asynchronously on the server. It then polls getexport and uses downloadexport to fetch the file once it is ready.

Run multi-step analytics pipelines in LangChain using your live GoatCounter pageview data and site configurations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GoatCounter MCP to LangChain

Create your Vinkius account to connect GoatCounter to LangChain 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 GoatCounter with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain live analytics into LangChain workflows

The `get_stats_total` tool lets your agent pull aggregate traffic numbers directly into a multi-step execution chain via our MCP Server. This means your LangChain workflows can verify raw traffic spikes before triggering downstream alerts or generating reports. You can route this data straight to other nodes in your graph. Your pipelines use real-world visitor metrics to decide whether to run deeper audits with `get_stats_page` or pause execution.

Monitor site health with this MCP Server

The `list_sites` tool retrieves all active domains under your account so your agent can audit configuration settings. If a site is missing or needs updates, the agent immediately calls `update_site` to correct the setup. This setup avoids manual dashboard checks. The agent handles configuration drifts on the fly and confirms the changes by fetching the updated state with `get_site`.

Automate data extraction and export pipelines

The `start_export` tool kicks off background data dumps when your LangChain run requires deep historical analysis. Your agent monitors the export status using `get_export` without blocking the rest of your chain. Once the export finishes, `download_export` pulls the raw CSV down for local processing. You get clean, raw data fed directly into your data frames or storage buckets.

Setup guide

Set up GoatCounter MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes GoatCounter tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "goatcounter-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent GoatCounter transactions"
    })
    print(result["messages"][-1].content)

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 GoatCounter. 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 GoatCounter 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 GoatCounter MCP in LangChain

You initialize the client using the LangChain MCP adapter and call get_tools to fetch the schema. Pass these tools directly into your agent constructor to let it run queries like `get_stats_hits`.

Yes, every tool execution shows up in LangSmith with complete input and output payloads. You can inspect the exact parameters passed to `get_stats_hits_path` and see the raw JSON response.

It handles any site your API key has access to. Your agent can call `list_sites` to discover targets and then query stats for each one individually.

The agent triggers `start_export` to run the job asynchronously on the server. It then polls `get_export` and uses `download_export` to fetch the file once it is ready.

This server runs in a secure, zero-trust MCP sandbox that handles your API key locally. Your visitor stats, pageviews, and site settings are never sent to third-party servers during processing.

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