How to Use the GoatCounter MCP in AutoGen

Q: How do AutoGen agents access GoatCounter tools?

You register the MCP server using the mcpservertools adapter and pass the tools list to your AssistantAgent. The adapter handles schema conversion automatically.

Q: Can AutoGen agents collaborate on GoatCounter metrics?

Yes, one agent can fetch raw numbers using getstatshits while another analyzes the trends. They share the context to build a unified report.

Q: How does AutoGen handle site creation in GoatCounter?

An agent can call createsite to provision a new tracking domain. Another agent can then verify the setup by calling getsite to confirm it is active.

Q: Can I track individual hits with AutoGen?

Your agents can use the counthits tool to send custom events or pageviews directly to your dashboard. This lets you log agent activities as they happen.

Let AutoGen agents debate and coordinate on your GoatCounter site configurations and traffic metrics.

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 AutoGen

Create your Vinkius account to connect GoatCounter to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-agent audits with this MCP Server

The `list_sites` tool allows a manager agent to discover all registered domains under your account. A separate auditor agent can then analyze each site's settings to identify configuration issues. If the auditor agent flags an issue, a writer agent can call `update_site` to apply the fix. This collaborative loop keeps your analytics settings perfectly aligned.

Debate traffic anomalies using live stats

The `get_stats_total` tool retrieves overall traffic counts so your MCP agents can monitor for sudden traffic spikes. An analysis agent might flag a spike, while a referral agent calls `get_stats_hits_path` to investigate the source. They negotiate whether the spike is organic or bot traffic. This consensus-driven approach ensures you get accurate insights without manual intervention.

Coordinate complex data exports

The `start_export` tool lets a data agent initiate a full backup of your visitor metrics. A coordinator agent tracks the progress using `get_export` to ensure the process runs smoothly. Once the file is ready, a storage agent uses `download_export` to fetch and archive the data. This team-based workflow automates your entire backup pipeline.

Setup guide

Set up GoatCounter MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes GoatCounter tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="GoatCounter_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent GoatCounter data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="GoatCounter_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent GoatCounter data")
    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 AutoGen

You register the MCP server using the mcp_server_tools adapter and pass the tools list to your AssistantAgent. The adapter handles schema conversion automatically.

Yes, one agent can fetch raw numbers using `get_stats_hits` while another analyzes the trends. They share the context to build a unified report.

An agent can call `create_site` to provision a new tracking domain. Another agent can then verify the setup by calling `get_site` to confirm it is active.

Your agents can use the `count_hits` tool to send custom events or pageviews directly to your dashboard. This lets you log agent activities as they happen.

The MCP server uses a zero-trust architecture that executes your API calls within an ephemeral sandbox. Your visitor counts and site settings are kept strictly private.

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