How to Use the Heroku (PaaS) MCP in CrewAI

Q: How can I use CrewAI to monitor all my Heroku (PaaS) apps for downtime?

Create a Monitor agent in your crew. Give it the listapps and listdynos tools. Its task is to periodically check all dynos and report any with a 'crashed' status to another agent for action.

Q: Can I build a CrewAI team that handles Heroku (PaaS) database migrations?

Absolutely. Assign a 'Coordinator' agent the togglemaintenancemode tool. A 'DBA' agent would run the migration script. The Coordinator enables maintenance, tells the DBA to run, waits for confirmation, then disables maintenance on your Heroku (PaaS) app.

Q: Can one CrewAI agent find a problem on Heroku (PaaS) and another fix it?

Yes, that's the core concept of CrewAI. One agent uses listdynos to find a hung worker dyno on a Heroku (PaaS) app. It then passes the app and dyno name to a 'Fixer' agent, whose only tool is restartspecificdyno.

Q: How do I give my CrewAI agents access to this MCP server?

You pass the Vinkius MCP endpoint URL into the mcps parameter when defining your Agent in CrewAI. You can use toolfilter to give different agents in the same crew access to different subsets of tools, enforcing role separation.

Q: How does CrewAI handle the privacy of Heroku config vars?

When an agent in your crew uses listconfigvars, secrets like DATABASEURL are loaded into that agent's context and potentially the crew's shared memory. Since CrewAI runs on your infrastructure, you are responsible for securing the execution environment and logs.

Deploy autonomous agent crews to manage your Heroku fleet. Let a Monitor agent watch for crashes and a DevOps agent fix them.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Heroku (PaaS) MCP to CrewAI

Create your Vinkius account to connect Heroku (PaaS) 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 Heroku (PaaS) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create a Heroku Operations Crew

With CrewAI, you assign roles. Create a 'Monitor' agent that constantly runs `list_apps` and then `list_dynos` for each app, watching for any that enter a 'crashed' state. When the Monitor spots a problem, it passes the app ID to a 'DevOps' agent. This second agent's only job is to take that ID and execute `restart_all_dynos` or `restart_specific_dyno` to resolve the issue. The two agents work together, autonomously.

Automated Security Audits

Set up a crew to perform continuous security checks. An 'Auditor' agent can periodically use `list_config_vars` on all production apps to check for missing secrets or keys that need rotation. If the Auditor finds an issue, it tasks a 'Compliance' agent to document it. This MCP server provides the specific tools for a specialized crew to enforce security policy 24/7.

Self-Provisioning Environments

A developer can ask a 'Provisioner' agent to 'create a new staging app for the frontend repo.' The agent uses `create_app` from this MCP server to build the shell. Once created, it passes the new app's info to a 'Configurator' agent. This agent then uses `list_config_vars` from the main production app and sets a sanitized version on the new staging app. The whole process is handled by the crew.

Setup guide

Set up Heroku (PaaS) 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 Heroku (PaaS) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Heroku (PaaS) 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="Heroku (PaaS) Analyst",
        goal="Access and analyze Heroku (PaaS) data via MCP.",
        backstory="Expert analyst with direct Heroku (PaaS) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Heroku (PaaS) 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 Heroku. 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 Heroku (PaaS) 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 Heroku (PaaS) MCP in CrewAI

Create a Monitor agent in your crew. Give it the `list_apps` and `list_dynos` tools. Its task is to periodically check all dynos and report any with a 'crashed' status to another agent for action.

Absolutely. Assign a 'Coordinator' agent the `toggle_maintenance_mode` tool. A 'DBA' agent would run the migration script. The Coordinator enables maintenance, tells the DBA to run, waits for confirmation, then disables maintenance on your Heroku (PaaS) app.

Yes, that's the core concept of CrewAI. One agent uses `list_dynos` to find a hung worker dyno on a Heroku (PaaS) app. It then passes the app and dyno name to a 'Fixer' agent, whose only tool is `restart_specific_dyno`.

You pass the Vinkius MCP endpoint URL into the `mcps` parameter when defining your Agent in CrewAI. You can use `tool_filter` to give different agents in the same crew access to different subsets of tools, enforcing role separation.

When an agent in your crew uses `list_config_vars`, secrets like `DATABASE_URL` are loaded into that agent's context and potentially the crew's shared memory. Since CrewAI runs on your infrastructure, you are responsible for securing the execution environment and logs.

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