How to Use the Heap MCP in LlamaIndex

Q: How does LlamaIndex work with the Heap MCP server?

You wrap the MCP client in a McpToolSpec, and LlamaIndex converts each tool, like trackevent, into a function the agent can call. Your agent can then use these tools to fetch live data for a RAG pipeline.

Q: Can I use LlamaIndex to search my Heap user data?

Yes. Your agent can call queryuserprofiles based on a natural language query, get the user profiles back, and then index them into a vector store. This allows for more complex semantic searches across your user base.

Q: How can I track many events from my LlamaIndex app to Heap?

Your agent can call the bulktrackevents tool. This is ideal for indexing large amounts of data or logging batch processes, letting you send many events in a single, efficient API request.

Turn Heap analytics data into a searchable knowledge base for your LlamaIndex RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Heap MCP to LlamaIndex

Create your Vinkius account to connect Heap 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 Heap with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Analytics Configuration

LlamaIndex can index the output of this server's tools. Have your agent call `get_event_definitions` and `get_segments`, then index that information into a vector store. Now, when you ask your agent, "What events are related to user signups?", it queries the index for a grounded answer, not a guess. This creates a living document of your analytics strategy. As your team adds new events or segments in Heap, your agent can periodically re-index them. It's a simple way to keep your agent's knowledge of your data model perfectly up to date.

Query User Histories with Natural Language

This isn't just about sending data to Heap; it's about making it useful. Use `query_user_profiles` to fetch user data, then let LlamaIndex index the results. You can now ask questions like, "Show me all premium users in Germany who signed up last month." Your agent translates that question into a structured call to `query_user_profiles`, gets the data, and gives you a clear answer. It effectively turns your raw Heap data into an interactive, conversational database.

Build a Self-Documenting LlamaIndex MCP Server

With the Heap MCP Server, your LlamaIndex agent can now document its own actions. When your agent performs an important task, it calls `track_event` to log the action and its outcome. This creates a detailed audit trail right inside your Heap project. The best part is that LlamaIndex can then index these very events. You can build a RAG pipeline that lets you ask, "What were the last five tasks you completed for user 123?" The answer will be grounded in the actual event data the agent logged itself.

Setup guide

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

You wrap the MCP client in a `McpToolSpec`, and LlamaIndex converts each tool, like `track_event`, into a function the agent can call. Your agent can then use these tools to fetch live data for a RAG pipeline.

Yes. Your agent can call `query_user_profiles` based on a natural language query, get the user profiles back, and then index them into a vector store. This allows for more complex semantic searches across your user base.

It's all about grounding. Your agent's knowledge isn't just based on static documents. It's augmented with live user data from Heap, so its answers reflect the current state of your product and users, not stale information.

Your agent can call the `bulk_track_events` tool. This is ideal for indexing large amounts of data or logging batch processes, letting you send many events in a single, efficient API request.

Yes. The server only touches user profile data explicitly requested by your agent via tools like `query_user_profiles`. Your Heap API key is secured on Vinkius servers and is never visible to the LlamaIndex client.

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