How to Use the Heap MCP in LangChain

Q: Can my LangChain agent track multiple Heap events at once?

Yes, your agent can use the bulktrackevents tool. This is built for high-throughput situations where you need to log a batch of interactions without hitting API rate limits one by one.

Q: How is this different from a direct Heap API integration?

This lets your agent decide what to track. Instead of you hardcoding API calls, your LangChain agent reasons about the user's goal and calls the right Heap tool, like adduserproperties, on its own.

Build data-aware LangChain agents that track user behavior in Heap and react to it in real-time.

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 LangChain

Create your Vinkius account to connect Heap to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Heap Actions for Full-Cycle Analytics

This server gives your LangChain agent a toolkit for product analytics. A new user signs up, and your agent can chain together the calls: first `track_event` for the signup, then `identify_user` to link their session, and finally `add_user_properties` to set their account tier. It's a full sequence your agent executes on its own. You can design more complex agentic workflows. For instance, an agent could run `query_user_profiles` to find users who haven't logged in for 90 days, then pass that list to `bulk_add_user_properties` to tag them for a re-engagement campaign. The output of one tool becomes the direct input for the next.

Give Your Agent Project-Level Context

Your agent shouldn't operate blind. Before it starts sending data, it can call `get_event_definitions` or `get_segments` to learn the current analytics setup in your Heap project. This means no more hardcoding event names or guessing property schemas; the agent adapts to your live configuration. It also handles compliance tasks. You can build a chain that responds to a GDPR request, finds the right person with `query_user_profiles`, and then calls `delete_user_data` to permanently remove them. You get an automated, auditable process instead of a manual chore.

Build a Data-Aware LangChain MCP Server

Connect this Heap MCP Server and your agent gets smarter. Instead of just following instructions, your agent can first call `query_user_profiles` to check a user's status before deciding on the next action. It turns your agent from a simple tool into a context-aware partner. Your agent can also monitor its own impact. After it completes a task, it can call `track_event` to log what it did and why. This creates a feedback loop right inside Heap, letting you analyze your agent's behavior alongside your users'.

Setup guide

Set up Heap MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Heap tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "heap-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Heap transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You get the tools list from the MCP client and pass it to your agent factory, like `create_agent`. LangChain then uses the tool schemas to decide when your agent should call `track_event` or `query_user_profiles`.

Yes, your agent can use the `bulk_track_events` tool. This is built for high-throughput situations where you need to log a batch of interactions without hitting API rate limits one by one.

Start by tracking events anonymously. Once the user signs in or identifies themselves, have your agent call `identify_user` to connect their anonymous activity to their permanent user ID. This keeps your funnels clean.

This lets your agent *decide* what to track. Instead of you hardcoding API calls, your LangChain agent reasons about the user's goal and calls the right Heap tool, like `add_user_properties`, on its own.

The server only touches the data your agent explicitly sends, like event names and user properties. All authentication is handled by a single Vinkius token, so your Heap API key is never exposed to the agent or the LangChain 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