How to Use the Heap MCP in AutoGen

Q: How do AutoGen agents use the tools from the Heap MCP server?

You provide the list of tools, like trackevent, to an AssistantAgent. The agent can then decide to call a tool as a step in its conversation with other agents to get data or perform an action.

Enable your AutoGen agent teams to debate and act on live Heap analytics data.

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 AutoGen

Create your Vinkius account to connect Heap to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fuel Agent Debates with Real User Data

AutoGen conversations need to be grounded in facts. With this server, an agent can pull a list of inactive users with `query_user_profiles`, and another agent can challenge the definition of 'inactive' by checking their properties. The debate is based on real data, not assumptions. This stops agents from just making things up. A 'ProductManagerAgent' might propose a new feature, and a 'DataAnalystAgent' can immediately check `get_event_definitions` in Heap to see if the required tracking is even in place. The discussion moves forward based on what's actually happening in your product.

Assign Agents to Manage Heap Data Hygiene

Set up a team of specialized agents to maintain your analytics. A 'ComplianceAgent' can be tasked with handling GDPR requests. When a request comes in, it works with another agent to find the user via `identify_user` and then executes `delete_user_data`. You could also create a 'DataQualityAgent' that periodically runs `query_user_profiles` looking for inconsistent data, and a 'FixerAgent' that uses `add_user_properties` or `add_account_properties` to clean it up. The agents work together to keep your Heap data reliable.

Create an Observability Agent for your AutoGen MCP Server

Designate one agent in your group as the 'Observer'. Its only job is to watch the conversation and the actions of other agents. When another agent calls a tool like `bulk_track_events`, the Observer agent calls `track_event` in Heap to log that the action occurred. This creates a meta-level audit log inside Heap. You're not just tracking user events; you're tracking your agent team's activity. It lets you analyze the performance and decision-making process of your entire multi-agent system, which is a core part of any serious MCP Server setup.

Setup guide

Set up Heap MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Heap tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Heap_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Heap data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Heap_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Heap data")
    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 AutoGen

You provide the list of tools, like `track_event`, to an `AssistantAgent`. The agent can then decide to call a tool as a step in its conversation with other agents to get data or perform an action.

Yes, and that's the whole point. One agent can be querying user data with `query_user_profiles` while another prepares a batch of events with `bulk_track_events`, all as part of their collaborative workflow to reach a goal.

You can have one agent identify a group of users, and another agent decide what properties to update. That second agent then calls `add_user_properties` or `bulk_add_user_properties` to execute the change in Heap after the team agrees.

It's about autonomous collaboration. With AutoGen, a team of agents can debate the *best* way to use your Heap data—for example, whether to tag a user or delete them—before any single action is taken.

The server only processes the event properties your agents explicitly include in calls like `track_event`. Vinkius manages the secure connection, so your actual Heap API key is never exposed to the AutoGen agents or their environment.

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