How to Use the Pirsch Analytics MCP in LlamaIndex

Q: How do I configure Pirsch Analytics with LlamaIndex?

Instantiate a BasicMCPClient and wrap it in McpToolSpec. Call totoollistasync() and pass the resulting functions to your FunctionAgent.

Q: Can LlamaIndex query Pirsch Analytics UTM sources?

Yes. The agent runs getstatisticsutmsource to pull campaign data. It can then index those results, allowing you to ask natural language questions about which marketing channels drive the most traffic.

Q: Is it possible to track LlamaIndex queries as events?

Your MCP agent can execute sendevent right after returning a generated response. This logs the interaction in your dashboard, giving you visibility into how often specific RAG pipelines are used.

Index zero-cookie analytics data into LlamaIndex. Query your traffic stats naturally.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pirsch Analytics MCP to LlamaIndex

Create your Vinkius account to connect Pirsch Analytics to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pirsch Analytics with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Embed raw analytics data into your vector store

The `get_statistics_overview` tool allows your LlamaIndex MCP agent to pull historical site performance and inject it straight into a queryable index. You pull monthly traffic reports and embed them alongside your marketing documents. When you ask why traffic dipped in November, the agent cross-references the actual API data. Granular metrics get the same treatment. By running `get_statistics_page` and `get_statistics_referrer`, you build a searchable knowledge base of top-performing content and traffic sources. The agent grounds its answers in real numbers rather than guessing based on outdated training data.

Log RAG application events to the MCP Server

The `send_event` tool lets you track exactly how users interact with your LlamaIndex application. Whenever a user executes a specific semantic search, the agent can fire a custom event to Pirsch. You see exactly which queries drive engagement without touching client-side code. High-volume query logging is built in. If your RAG system processes hundreds of documents a minute, it can use `send_event_batch` to log those interactions efficiently. The tracking happens entirely server-side, keeping your frontend clean and fast.

Index active domains and visitor trends

The `list_domains` tool pulls your entire Pirsch portfolio so LlamaIndex can map your tracking infrastructure. You can ask your agent which domains are currently active, and it retrieves the exact list from the API before synthesizing a response. Real-time checks work too. The agent can trigger `get_statistics_active` to fetch current live visitors, combining that figure with historical vector data to determine if a current traffic spike is anomalous. All data access is controlled via your allowed tools filter.

Setup guide

Set up Pirsch Analytics 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 Pirsch Analytics 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 Pirsch Analytics tools.",
)
response = await agent.run("List recent Pirsch Analytics 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 Pirsch Analytics. 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 Pirsch Analytics 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 Pirsch Analytics MCP in LlamaIndex

Instantiate a `BasicMCPClient` and wrap it in `McpToolSpec`. Call `to_tool_list_async()` and pass the resulting functions to your `FunctionAgent`.

Yes. The agent runs `get_statistics_utm_source` to pull campaign data. It can then index those results, allowing you to ask natural language questions about which marketing channels drive the most traffic.

Your MCP agent can execute `send_event` right after returning a generated response. This logs the interaction in your dashboard, giving you visibility into how often specific RAG pipelines are used.

Use the LlamaIndex allowed tools filter during setup. You can expose read-only endpoints like `get_statistics_visitor` while blocking the agent from calling `create_domain`.

The Pirsch MCP server never exposes IP addresses or persistent identifiers. When your LlamaIndex application indexes referrer data or active visitor counts, it only processes anonymous, aggregated statistics that comply with strict privacy laws.

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