How to Use the H2O.ai MCP in Windsurf

Q: How do I connect the H2O.ai MCP Server to Windsurf?

Open your Windsurf settings and add the server to your mcpconfig.json file under the mcpServers block. Once saved, click Refresh in the MCP panel, and Cascade will instantly auto-discover the tools like listjobs and getframe.

Q: How does Windsurf track active H2O.ai training runs?

Windsurf uses the listjobs tool to check the status of your active training tasks. Cascade monitors these runs in the background and notifies you directly in the chat panel the moment the training cycle finishes.

Q: How is my H2O.ai data frame privacy protected?

All data frame metadata and model structures fetched via getframe remain strictly inside your local Windsurf environment. Vinkius runs the server in an isolated sandbox, ensuring your proprietary training data never leaks to external servers.

Let Windsurf Cascade autonomously track H2O.ai training jobs, audit data frames, and inspect model health without manual context switching.

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 Windsurf

Create your Vinkius account to connect H2O.ai to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step model audits using Windsurf Cascade

Let Cascade scan your H2O.ai cluster without babying the terminal. When you ask Cascade to verify your active models, it automatically triggers `list_models` to find the target before running `get_model` to inspect the hyperparameters inside the Windsurf editor. You don't have to prompt for each individual step or manually copy-paste H2O.ai model IDs. This MCP server lets Windsurf chain these calls in the background, giving you the exact state of your deployed models while you focus on writing your application logic.

Real-time tracking of active training jobs

Stop manually refreshing your cluster UI to see if an H2O.ai model finished training. When you prompt Cascade to check on your pipeline, it uses `list_jobs` to pull the active queue and inspects the status directly within your Windsurf workspace. Because Cascade can execute commands autonomously, it handles the H2O.ai polling loop for you. It checks the active jobs, waits if needed, and notifies you in Windsurf the second the status changes, saving you from constant context switching.

Instant inspection of cluster data frames via this MCP Server

Inspecting H2O.ai training data shouldn't require spinning up a separate notebook. Windsurf uses `list_frames` to locate your training sets and pulls details with `get_frame` to verify column types or row counts directly in your active project. Cascade parses the returned H2O.ai frame schema to ensure your local preprocessing scripts match what the cluster expects. If there's a mismatch, Cascade updates your Windsurf workspace files to align with the active frame.

Setup guide

Set up H2O.ai MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my H2O.ai payment history." If connected, Cascade will call the H2O.ai tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "h2oai-mcp": {
      "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 Windsurf

Open your Windsurf settings and add the server to your `mcp_config.json` file under the `mcpServers` block. Once saved, click Refresh in the MCP panel, and Cascade will instantly auto-discover the tools like `list_jobs` and `get_frame`.

Yes, Cascade specializes in chaining actions autonomously. You can ask it to find a specific model and check its data frame, and it will run `list_models`, grab the ID, and then call `get_frame` without requiring intermediate prompts.

Windsurf uses the `list_jobs` tool to check the status of your active training tasks. Cascade monitors these runs in the background and notifies you directly in the chat panel the moment the training cycle finishes.

No, this MCP server communicates directly with your cluster over HTTP. Your agent only needs the server connection configured to run status checks and pull model metadata.

All data frame metadata and model structures fetched via `get_frame` remain strictly inside your local Windsurf environment. Vinkius runs the server in an isolated sandbox, ensuring your proprietary training data never leaks to 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