How to Use the H2O.ai MCP in Claude Code

Q: How do I configure the H2O.ai MCP Server in Claude Code?

Run the command claude mcp add --transport http h2oai -- in your terminal, making sure all flags come before the server name. You can verify the installation by running claude mcp list.

Q: How does Claude Code handle large H2O.ai data frames?

The MCP server uses getframe to pull structural metadata and summaries rather than downloading the entire dataset, keeping terminal output lightweight and fast.

Q: How is my H2O.ai cluster status data secured?

All requests to cloudstatus and model endpoints use ephemeral tokens managed securely by the Vinkius platform. Your cluster credentials and node health metrics never touch Claude Code's external servers.

Manage your H2O.ai models, verify data frames, and monitor training jobs directly from your terminal using Claude Code CLI.

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 Claude Code

Create your Vinkius account to connect H2O.ai to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless H2O.ai model monitoring via Claude Code

Keep your terminal clean and your pipelines running. Claude Code uses `list_models` and `get_model` to dump H2O.ai model metadata straight to your shell, letting you inspect training parameters or performance metrics without opening a browser. You can pipe this H2O.ai output directly into other command-line utilities or let Claude Code write quick bash scripts to automate your deployments. It brings full cluster visibility straight to your SSH session.

Terminal-based H2O.ai job auditing via MCP

Track your H2O.ai cluster's workload without leaving the command line. Claude Code runs `list_jobs` to list active tasks, checking progress and identifying failed runs instantly so you can debug them on the spot. Because Claude Code runs entirely in the terminal, you can integrate these H2O.ai checks into your existing shell scripts or cron jobs, making it easy to build lightweight automation around your model training. No more context switching to an external dashboard when everything is accessible from the prompt.

Rapid H2O.ai data frame checks in the terminal

Verify your datasets instantly using `list_frames` and `get_frame` directly from the Claude Code CLI. The agent pulls the exact dimensions and types of your H2O.ai training frames, helping you catch data issues before kickstarting a new training run. This is perfect for quick sanity checks during remote debugging sessions, allowing you to confirm that your H2O.ai data uploaded successfully without needing a heavy desktop client. You run a single command and get instant feedback.

Setup guide

Set up H2O.ai MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see h2oai-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest H2O.ai transactions." It will automatically discover and invoke the available H2O.ai tools.

Terminal

claude mcp add --transport http h2oai-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the H2O.ai MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "h2oai-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

Run the command `claude mcp add --transport http h2oai -- ` in your terminal, making sure all flags come before the server name. You can verify the installation by running `claude mcp list`.

Yes, because Claude Code is terminal-only, you can run it in headless environments to check active training tasks using `list_jobs` and trigger downstream deployment scripts based on the results.

The MCP server uses `get_frame` to pull structural metadata and summaries rather than downloading the entire dataset, keeping terminal output lightweight and fast.

Yes, you can configure different server endpoints or pass specific cluster configurations through the MCP environment settings to switch between staging and production environments.

All requests to `cloud_status` and model endpoints use ephemeral tokens managed securely by the Vinkius platform. Your cluster credentials and node health metrics never touch Claude Code's external servers.

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