How to Use the Heap MCP in CrewAI

Q: How can a CrewAI team collaborate to manage user segments in Heap?

Assign one agent to use the MCP tools getsegments and queryuserprofiles to find targets. Then, have it pass the user list to another agent whose job is to use adduserproperties to update them.

Q: Can different agents in a CrewAI crew use different Heap tools via CrewAI?

Yes. You can use toolfilter when setting up the MCP server in CrewAI. This lets you assign specific tools, like deleteuserdata, to a trusted 'Admin' agent while other agents only get read-only tools.

Q: What's a good agent structure in CrewAI for monitoring Heap analytics?

A two-agent crew works well. An 'Analyst' agent uses queryuserprofiles to find interesting behavior, and a 'Responder' agent uses adduserproperties to tag those users in Heap for action.

Q: Can I use CrewAI to build a self-correcting data quality system for Heap?

You can build a data monitoring system. An agent can use geteventdefinitions to find problems and report them. The Heap tools don't allow for correcting definitions, but they let your crew find the issues fast.

Deploy autonomous agent crews to monitor, manage, and act on your Heap analytics with CrewAI.

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 CrewAI

Create your Vinkius account to connect Heap to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a User Behavior Watchdog Crew

Assign roles to a crew of agents to watch your product analytics. A 'Scout' agent can run `query_user_profiles` every hour, looking for users who match criteria for churn risk. It doesn't act; it just finds them. The Scout passes its findings to a 'Marketer' agent. This agent then uses `add_user_properties` to tag the user's profile in Heap, automatically adding them to a re-engagement segment. The whole MCP-driven process runs on its own.

Your MCP Server for Data Governance

Good data requires maintenance. A 'Librarian' agent can be tasked to periodically run `get_event_definitions` and check for inconsistent or deprecated event names. When the Librarian finds a problem, it reports to a 'Janitor' agent. This agent can't delete definitions, but it can `query_user_profiles` to find who sent the bad data and log the issue for a human developer to review. It’s an automated data quality check.

Let Agents Manage Their Own API Usage

Avoid hitting API limits. Designate a 'Controller' agent in your crew to monitor your Heap usage. Its only job is to call `get_api_usage` on a schedule. If API calls are spiking, the Controller can communicate to other agents in the crew. It can instruct them to switch from `track_event` to the more efficient `bulk_track_events` tool until usage drops. Your crew becomes self-regulating.

Setup guide

Set up Heap MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Heap tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Heap Analyst",
    goal="Access and analyze Heap data via MCP.",
    backstory="Expert analyst with direct Heap access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Heap transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Heap Analyst",
        goal="Access and analyze Heap data via MCP.",
        backstory="Expert analyst with direct Heap access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Heap transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Assign one agent to use the MCP tools `get_segments` and `query_user_profiles` to find targets. Then, have it pass the user list to another agent whose job is to use `add_user_properties` to update them.

Yes. You can use `tool_filter` when setting up the MCP server in CrewAI. This lets you assign specific tools, like `delete_user_data`, to a trusted 'Admin' agent while other agents only get read-only tools.

A two-agent crew works well. An 'Analyst' agent uses `query_user_profiles` to find interesting behavior, and a 'Responder' agent uses `add_user_properties` to tag those users in Heap for action.

You can build a data *monitoring* system. An agent can use `get_event_definitions` to find problems and report them. The Heap tools don't allow for correcting definitions, but they let your crew find the issues fast.

Vinkius security is key here. Each tool call from any agent is executed in a separate, sandboxed V8 Isolate. Even within the same crew, one agent's call to `get_segments` has no access to the memory or data from another agent's call to `query_user_profiles`.

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