How to Use the Kissmetrics MCP in LlamaIndex

Q: How do I add the Kissmetrics MCP Server to my LlamaIndex pipeline?

Install the tool using pip install llama-index-tools-mcp and set up the BasicMCPClient. Wrap the client in McpToolSpec to expose the tracking and querying tools directly to your FunctionAgent.

Q: Can LlamaIndex index historical event data from Kissmetrics?

Yes, the agent calls querymetricdata to fetch historical values and indexes those results into your vector store. This lets you run semantic searches over past performance trends and user cohort behaviors.

Q: How does LlamaIndex handle unknown user identities?

The agent uses aliasidentities to merge anonymous session indexes with identified user profiles. This ensures your vector index doesn't create duplicate, fragmented nodes for the same human user.

Q: Does this Kissmetrics integration support real-time event tracking in LlamaIndex?

Yes, you can configure your agent to run recordevent whenever a user performs a search or retrieves a document. This tracks how users interact with your RAG system, feeding that behavior back into your MCP server.

Index live Kissmetrics behavior data directly into your LlamaIndex vector store using this MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kissmetrics MCP to LlamaIndex

Create your Vinkius account to connect Kissmetrics 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 Kissmetrics with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index user behavior profiles into your vector index

`set_person_properties` updates your user profiles with custom attributes that your RAG pipeline can index immediately. Your LlamaIndex agent uses this tool to log user preferences, converting raw attributes into searchable metadata. By indexing these properties, your agent answers questions based on actual user profiles rather than static documents. The agent queries this live index during conversations to personalize its responses based on the user's logged history.

Search live conversion funnels using LlamaIndex RAG

`list_event_types` retrieves all active events tracked in your account so your agent knows what metrics are available to index. LlamaIndex uses this schema to map out the structure of your conversion funnels, turning raw events into searchable context. Your agent queries this structural index to find out which events matter for specific user journeys. Instead of guessing event names, the agent searches the indexed schemas to build accurate queries for your reports.

Ground your LlamaIndex queries in real Kissmetrics data

`query_people_count` extracts exact user volumes matching specific segment criteria to feed directly into your RAG context. When a user asks about churn or conversion, the agent calls this tool alongside `query_metric_data` to get exact figures. This setup eliminates hallucinated metrics by forcing the agent to retrieve actual numbers before answering. LlamaIndex embeds these query results into the prompt context, guaranteeing that every report your agent generates matches your actual database.

Setup guide

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

Install the tool using `pip install llama-index-tools-mcp` and set up the `BasicMCPClient`. Wrap the client in `McpToolSpec` to expose the tracking and querying tools directly to your `FunctionAgent`.

Yes, the agent calls `query_metric_data` to fetch historical values and indexes those results into your vector store. This lets you run semantic searches over past performance trends and user cohort behaviors.

The agent uses `alias_identities` to merge anonymous session indexes with identified user profiles. This ensures your vector index doesn't create duplicate, fragmented nodes for the same human user.

Yes, you can configure your agent to run `record_event` whenever a user performs a search or retrieves a document. This tracks how users interact with your RAG system, feeding that behavior back into your MCP server.

All event data and identity payloads pass through V8-isolated MCP sandboxes that destroy data immediately after the tool execution ends. Your API keys are encrypted at rest and never exposed to the LLM or external vector stores.

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