How to Use the GoatCounter MCP in LlamaIndex

Q: Can LlamaIndex query specific page stats from GoatCounter?

Yes, your agent can call getstatshitspath to pull referral data for any specific URL path. It then uses this context to answer questions about traffic sources.

Q: How does LlamaIndex avoid hallucinations using GoatCounter?

The agent pulls cold hard numbers using getstatstotal before generating any reports. This ensures the output is strictly bounded by the retrieved JSON.

Q: Can I manage my analytics sites through the index?

Your agent can call getsite to retrieve configuration details and index them. If settings are off, the agent can use updatesite to correct them.

Index your GoatCounter visitor stats directly into LlamaIndex vector stores for grounded, hallucination-free RAG.

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 LlamaIndex

Create your Vinkius account to connect GoatCounter to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live analytics with this MCP Server

The `get_stats_hits` tool fetches traffic trends across all paths to feed directly into your LlamaIndex document store. Your RAG system indexes these real-time paths so your agent answers user queries using actual traffic data. This prevents your LLM from guessing which pages are popular. By grounding queries in actual numbers, your search results reflect reality.

Query deep visitor statistics semantically

The `get_stats_page` tool breaks down visitor data by categories like browsers or operating systems. LlamaIndex indexes these breakdowns, allowing you to ask natural language questions about your audience's tech stack. Your agent calls `get_stats_page_detail` to resolve specific browser versions when a user asks for granular details. This turns raw analytics into a searchable knowledge base.

Feed raw exports into your vector index

The `start_export` tool allows your agent to request a complete database dump for long-term trend analysis. LlamaIndex monitors the job with `get_export` and downloads the payload when ready. After using `download_export`, your MCP pipeline parses the raw data and builds a vector index. This lets you run semantic search over months of historical visitor activity.

Setup guide

Set up GoatCounter MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all GoatCounter MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to GoatCounter tools.",
)
response = await agent.run("List recent GoatCounter data")

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 LlamaIndex

Use the LlamaIndex MCP client to point to the server and convert the tools using McpToolSpec. Pass these tools to your FunctionAgent to let it fetch live metrics.

Yes, your agent can call `get_stats_hits_path` to pull referral data for any specific URL path. It then uses this context to answer questions about traffic sources.

The agent pulls cold hard numbers using `get_stats_total` before generating any reports. This ensures the output is strictly bounded by the retrieved JSON.

Your agent can call `get_site` to retrieve configuration details and index them. If settings are off, the agent can use `update_site` to correct them.

All site configurations and API keys are isolated within an ephemeral MCP sandbox. Your credentials and traffic data are never stored or exposed to external networks.

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