How to Use the Modal (Serverless AI Infrastructure) MCP in CrewAI

Q: Can a CrewAI agent stop a Modal (Serverless AI Infrastructure) app?

Yes, if you include the stopapp tool in the agent's definition. Make sure the agent has the right instructions to avoid accidental shutdowns.

Deploy autonomous infrastructure monitoring crews for Modal (Serverless AI Infrastructure) using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Modal (Serverless AI Infrastructure) MCP to CrewAI

Create your Vinkius account to connect Modal (Serverless AI Infrastructure) 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 Modal (Serverless AI Infrastructure) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor infrastructure with CrewAI

Assign a dedicated agent to run `list_apps` and `get_app` on a schedule. Your crew watches for drift while you focus on shipping code. It turns infrastructure management into a passive task. The agent alerts you only if it spots an issue.

Manage GPU resources with CrewAI

Let your crew inspect GPU deployments using `get_deployment`. It ensures your expensive instances are actually being utilized by active tasks. You save money by having an agent kill inactive but expensive apps. It keeps your compute footprint tight.

Verify secrets with CrewAI

Use `list_secrets` to have an agent audit your configuration access. It confirms that your deployments have the right environment variables mapped. This is a standard security check that happens automatically. You avoid deployment failures due to missing keys.

Setup guide

Set up Modal (Serverless AI Infrastructure) 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 Modal (Serverless AI Infrastructure) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Modal (Serverless AI Infrastructure) 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 Modal. 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 Modal (Serverless AI Infrastructure) 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 Modal (Serverless AI Infrastructure) MCP in CrewAI

Pass the server URL directly into your agent's mcps list. The crew will gain access to the tools like `list_apps` immediately.

Yes, if you include the `stop_app` tool in the agent's definition. Make sure the agent has the right instructions to avoid accidental shutdowns.

It is, because every request is authenticated. You can restrict which agents have access to which tools for added safety.

The agent receives the error output from the tool and can decide to try again or report the issue to you. It's built into the framework's execution loop.

It exposes your deployment IDs, volume names, and secret references. It does not expose your actual application source code or sensitive 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