How do I find my Heap App ID and API Key?

Log in to Heap, go to **Account > Projects**, and select your project. Your **App ID** will be visible there. For the **API Key**, navigate to the API section in your project settings to generate a server-side key.

Can I track events server-side through this integration?

Yes! Use the `track_event` tool. You provide the user identity, event name, and optional properties. This is perfect for capturing actions that happen outside the client browser.

How do I update user properties in bulk?

Use the `bulk_add_user_properties` tool. You must provide a JSON array containing objects with `identity` and `properties` for each user you wish to update.

Is the data deletion tool permanent?

Yes. The `delete_user_data` tool triggers a permanent deletion of the user identity and all historical data from Heap, helping you comply with GDPR and CCPA requests.

Heap MCP Server for LlamaIndex 12 tools — connect in under 2 minutes

Name: Heap
Availability: InStock
Author: Vinkius

docs.llamaindex.ai/en/stable/module_guides/tools/mcp

Built by Vinkius GDPR 12 Tools Framework

LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add Heap as an MCP tool provider through Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    mcp_client = BasicMCPClient("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    agent = FunctionAgent(
        tools=tools,
        llm=OpenAI(model="gpt-4o"),
        system_prompt=(
            "You are an assistant with access to Heap. "
            "You have 12 tools available."
        ),
    )

    response = await agent.run(
        "What tools are available in Heap?"
    )
    print(response)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Heap MCP Server

Connect your Heap.io analytics account to any AI agent and take full control of your product data and user identity management through natural conversation.

LlamaIndex agents combine Heap tool responses with indexed documents for comprehensive, grounded answers. Connect 12 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.

What you can do

Event Tracking — Send custom server-side events to Heap to capture granular user interactions.
User Identification — Associate anonymous sessions with specific identities and set custom profile properties.
Segment Management — List all segments defined in your project to understand your user cohorts.
Event Definitions — Access your custom event definitions to stay aligned with your analytics schema.
Bulk Operations — Track multiple events or update several user profiles in a single high-throughput request.
GDPR Compliance — Permanently delete user data directly from the chat interface when requested.
Query Profiles — Filter and retrieve user profiles based on specific behavior or attributes.

The Heap MCP Server exposes 12 tools through the Vinkius. Connect it to LlamaIndex in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Heap to LlamaIndex via MCP

Follow these steps to integrate the Heap MCP Server with LlamaIndex.

Install dependencies

Run pip install llama-index-tools-mcp llama-index-llms-openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 12 tools from Heap

Why Use LlamaIndex with the Heap MCP Server

LlamaIndex provides unique advantages when paired with Heap through the Model Context Protocol.

Data-first architecture: LlamaIndex agents combine Heap tool responses with indexed documents for comprehensive, grounded answers

Query pipeline framework lets you chain Heap tool calls with transformations, filters, and re-rankers in a typed pipeline

Multi-source reasoning: agents can query Heap, a vector store, and a SQL database in a single turn and synthesize results

Observability integrations show exactly what Heap tools were called, what data was returned, and how it influenced the final answer

Heap + LlamaIndex Use Cases

Practical scenarios where LlamaIndex combined with the Heap MCP Server delivers measurable value.

Hybrid search: combine Heap real-time data with embedded document indexes for answers that are both current and comprehensive

Data enrichment: query Heap to augment indexed data with live information before generating user-facing responses

Knowledge base agents: build agents that maintain and update knowledge bases by periodically querying Heap for fresh data

Analytical workflows: chain Heap queries with LlamaIndex's data connectors to build multi-source analytical reports

Heap MCP Tools for LlamaIndex (12)

These 12 tools become available when you connect Heap to LlamaIndex via MCP:

add_account_properties

Add or update properties for an account (group of users)

add_user_properties

Add or update custom properties for a user profile

bulk_add_user_properties

Update properties for multiple users in a single request

bulk_track_events

Track multiple events concurrently for high-throughput

delete_user_data

Permanently delete a user and all their associated data (GDPR)

get_api_usage

Check current API usage and project status

get_event_definitions

List all custom event definitions in Heap

get_my_profile

Get information about the authenticated API key

get_segments

List all segments defined in your Heap project

identify_user

Associate an anonymous session with a specific user identity

query_user_profiles

Query and filter user profiles based on criteria

track_event

Properties should be a JSON string. Track a server-side event for a user in Heap

Example Prompts for Heap in LlamaIndex

Ready-to-use prompts you can give your LlamaIndex agent to start working with Heap immediately.

"Track event 'Checkout Started' for user 'user_992' with properties {'value': 49.99}."

"List all active segments in the project."

"Identify user 'anon_552' as 'john.doe@example.com'."

Troubleshooting Heap MCP Server with LlamaIndex

Common issues when connecting Heap to LlamaIndex through the Vinkius, and how to resolve them.

BasicMCPClient not found

Install: pip install llama-index-tools-mcp

Heap + LlamaIndex FAQ

Common questions about integrating Heap MCP Server with LlamaIndex.

How does LlamaIndex connect to MCP servers?

Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.