How to Use the H2O.ai MCP in CrewAI

Q: How do I connect H2O.ai to CrewAI?

You can pass your Vinkius endpoint directly into the mcps list when defining your CrewAI agents. For more control, import MCPServerHTTP from crewai.mcp to filter which tools are exposed to specific agents.

Q: How do CrewAI agents handle long-running H2O.ai jobs?

Agents use listjobs to check the status of active training runs. Because CrewAI agents can run in loops or sequential tasks, they will poll the status until the job completes before moving to the next task.

Q: How is my H2O.ai cluster status data kept secure by this MCP Server?

All calls to cloudstatus and job lists run through a secure, isolated V8 sandbox. Your credentials and cluster health metrics are never exposed or stored. The connection remains strictly ephemeral and encrypted.

Deploy specialized Python agent teams to monitor H2O.ai jobs and manage data frames autonomously using CrewAI and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect H2O.ai MCP to CrewAI

Create your Vinkius account to connect H2O.ai 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 H2O.ai with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent H2O.ai operations using CrewAI

The `list_jobs` tool lets your CrewAI agents divide and conquer tasks like model evaluation and data validation over MCP. Let a team of specialized agents manage your machine learning lifecycle instead of relying on manual oversight. One agent can focus on tracking active training runs, while a separate analyst agent inspects completed models with `get_model`. They share memory to make smart deployment decisions.

Autonomous data drift and schema monitoring

The `list_frames` tool locates new training inputs so your data auditor agent can analyze their structure using `get_frame`. Keep your training data sets under constant surveillance without writing custom cron jobs. If the agent detects schema changes, it alerts the rest of the crew to halt downstream training jobs. This prevents corrupt data from poisoning your production models.

Smart cluster resource management

The `cloud_status` tool checks cluster health before any team member initiates a heavy task, avoiding cluster downtime. A dedicated infrastructure agent handles this monitoring task autonomously. The crew coordinates its work schedule based on the cluster's actual capacity. This keeps your queue clear and ensures critical model evaluations complete on time.

Setup guide

Set up H2O.ai 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 H2O.ai tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="H2O.ai Analyst",
    goal="Access and analyze H2O.ai data via MCP.",
    backstory="Expert analyst with direct H2O.ai access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent H2O.ai 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="H2O.ai Analyst",
        goal="Access and analyze H2O.ai data via MCP.",
        backstory="Expert analyst with direct H2O.ai access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent H2O.ai 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 H2O.ai. 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 H2O.ai 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 H2O.ai MCP in CrewAI

You can pass your Vinkius endpoint directly into the `mcps` list when defining your CrewAI agents. For more control, import `MCPServerHTTP` from `crewai.mcp` to filter which tools are exposed to specific agents.

Yes, CrewAI supports hierarchical execution. A manager agent can delegate the task of listing models via `list_models` to a researcher, who then passes the model IDs to an analyst to inspect details with `get_model`.

Agents use `list_jobs` to check the status of active training runs. Because CrewAI agents can run in loops or sequential tasks, they will poll the status until the job completes before moving to the next task.

Yes, you can use a tool filter during setup to restrict access. For instance, you can allow your monitoring agent to run `cloud_status` while blocking it from accessing detailed data frames.

All calls to `cloud_status` and job lists run through a secure, isolated V8 sandbox. Your credentials and cluster health metrics are never exposed or stored. The connection remains strictly ephemeral and encrypted.

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