How to Use the Fathom Analytics MCP in LlamaIndex

Q: Can I use this Fathom Analytics MCP Server for LlamaIndex RAG?

Yes, you can query live metrics using getvisitors and feed the results straight into your LlamaIndex vector index. This allows your RAG application to answer user questions using live, accurate traffic data.

Q: Does the LlamaIndex integration support resource loading?

Yes, you can set includeresources=True on your tool spec to let LlamaIndex load raw data structures. This is particularly useful for parsing complex arrays returned by getdevicestats.

Index Fathom Analytics data into your LlamaIndex RAG pipeline for hallucination-free reporting.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fathom Analytics MCP to LlamaIndex

Create your Vinkius account to connect Fathom Analytics 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 Fathom Analytics with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index site traffic data into semantic vector stores

Stop letting your AI guess your traffic numbers. This integration pulls live data using `get_visitors` and `get_pageviews` and indexes it directly into your LlamaIndex vector store. Your QA agents can then query this index to get real, grounded answers about your site performance. By converting raw tool outputs into searchable document nodes, you eliminate hallucinations. When you ask your agent about monthly growth, it retrieves actual data pulled from `list_sites` instead of making up metrics.

Search past analytics queries with LlamaIndex RAG

Turn your raw analytics history into a queryable knowledge base. LlamaIndex takes outputs from tools like `get_top_pages` and `get_referrers` and stores them alongside your documentation. This lets you run complex semantic searches over your historical traffic patterns. Your agent can cross-reference live traffic with old marketing reports. It queries `get_device_stats` to see current mobile trends, then checks the index to see if past mobile campaigns matched this behavior.

Filter Fathom Analytics MCP Server tools dynamically

You don't always want your RAG agent to have full access to every admin tool. LlamaIndex lets you apply an allowed_tools filter to restrict the agent to specific queries like `get_current_visitors` or `list_events`. This keeps your account configuration secure while still allowing traffic analysis. Setting this up requires only a few lines of code during initialization. You can expose read-only metrics to public-facing query agents while keeping administrative tools like `get_account_info` restricted.

Setup guide

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

Initialize the MCP client with the server URL and wrap it in McpToolSpec. You can then call to_tool_list_async() to expose tools like `get_pageviews` directly to your LlamaIndex agent for indexing.

Yes, you can query live metrics using `get_visitors` and feed the results straight into your LlamaIndex vector index. This allows your RAG application to answer user questions using live, accurate traffic data.

LlamaIndex grounds its answers in the exact payloads returned by tools like `get_referrers`. Because the agent queries the live API instead of relying on its training data, it cannot hallucinate your traffic metrics.

Yes, you can set include_resources=True on your tool spec to let LlamaIndex load raw data structures. This is particularly useful for parsing complex arrays returned by `get_device_stats`.

Your visitor metrics and site lists remain completely private because all tool executions run inside Vinkius's secure MCP sandbox. Your Fathom API token is never exposed to the LLM or stored in your vector database.

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