How to Use the Klaviyo MCP in LlamaIndex

Q: How do I initialize the Klaviyo tools in LlamaIndex?

Use BasicMCPClient to connect to the server, then wrap it with McpToolSpec. Call totoollistasync() and pass the array to your FunctionAgent.

Q: Does LlamaIndex index my Klaviyo campaign metrics automatically?

Not by default. You need to instruct your agent to call listmetrics and route that specific output into your document store for embedding.

Q: Can I restrict which tools the agent accesses?

Absolutely. Use the allowedtools filter when setting up the spec. You might want an agent that only reads lists but cannot trigger events.

Index Klaviyo campaigns into LlamaIndex to build searchable marketing knowledge bases.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Klaviyo MCP to LlamaIndex

Create your Vinkius account to connect Klaviyo 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 Klaviyo with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

LlamaIndex MCP Server Integration

Stop hallucinating your marketing metrics. This MCP server lets your LlamaIndex application pull live data directly from `list_campaigns` and `list_email_templates`. The agent grabs the actual copy you sent last week and indexes it into your vector store. Now your RAG pipeline has real context. When you ask your agent why the summer sale failed, it queries the semantic index of your past broadcasts. It grounds every answer in the hard data returned by `list_metrics`.

Semantic Profile Searching

Standard APIs force you to search by exact ID. LlamaIndex handles this differently by pulling bulk data via `list_profiles` and `list_segments`, then embedding those records. You can query your customer base using natural language instead of writing complex SQL. Want to find users who complain about shipping but buy high-margin items? Your MCP-enabled agent pulls the raw data, indexes it, and runs a semantic search over the text. It uses `get_profile` to pull specific details when it finds a match.

Event and Flow Auditing

Marketing automation gets messy fast. You can point your FunctionAgent at `list_automated_flows` and `list_marketing_lists` to map out your entire logic tree. The agent reads the structure and stores it in a queryable index. This means you can ask your system plain-English questions about your setup. If you need to know which flows fire a specific `track_event` trigger, the agent searches its index. It even checks `list_webhooks` to see where external data enters the system.

Setup guide

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

Use `BasicMCPClient` to connect to the server, then wrap it with `McpToolSpec`. Call `to_tool_list_async()` and pass the array to your `FunctionAgent`.

It handles both. Your agent can read existing records for RAG context, and it can execute `create_profile` to push new leads into your database.

Not by default. You need to instruct your agent to call `list_metrics` and route that specific output into your document store for embedding.

Absolutely. Use the `allowed_tools` filter when setting up the spec. You might want an agent that only reads lists but cannot trigger events.

We run a zero-trust architecture. When your application pulls names and phone numbers from `list_profiles`, the connection is authenticated via one endpoint token. The ephemeral container dies immediately after the session.

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