How to Use the MLflow (ML Lifecycle Management) MCP in Windsurf

Q: How does Windsurf use the MLflow (ML Lifecycle Management) MCP Server to track runs?

Cascade calls searchruns to pull your active training sessions directly into your workspace context. It reads the parameters and metrics in real time, allowing you to compare models without leaving your IDE.

Q: Can Windsurf automate model deployment steps with MLflow (ML Lifecycle Management)?

Yes, it can. Cascade uses searchregisteredmodels to check the current production status of your models and can write the deployment scripts based on those active registry tags.

Q: How do I configure MLflow (ML Lifecycle Management) in my Windsurf workspace?

You add the server config to your mcpconfig.json file. Once the MCP connection is live, Cascade automatically discovers the tools and starts querying your experiments when you ask about your training runs.

Q: Do I need to manually copy run IDs for Cascade to work?

You do not. Cascade uses searchexperiments and getrun to find the exact run IDs itself, pulling the required metrics automatically based on your natural language prompt.

Let Windsurf autonomously query your MLflow registry, track training runs, and audit models 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 MLflow (ML Lifecycle Management) MCP to Windsurf

Create your Vinkius account to connect MLflow (ML Lifecycle Management) 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 MLflow (ML Lifecycle Management) with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit model runs autonomously in Windsurf

The `search_runs` tool gives Cascade direct access to your active MLflow training runs via this MCP Server so it can pinpoint specific metrics. You tell Cascade to find the best performing model from last night, and it pulls the exact run data to compare loss curves. It doesn't stop at listing them. Cascade automatically feeds those run IDs into `get_run` to extract the exact hyperparameters that led to that performance. You get a clean breakdown of the winning configuration right in your editor.

Inspect artifacts and model outputs

The `list_artifacts` tool lets your agent inspect the specific files, plots, and weights generated during a training run. Cascade reads this structure to verify that your model saved correctly and that training plots exist. Instead of jumping to a browser to hunt for files, you ask the agent to verify the output directory. It runs the check, finds the serialized model, and prepares your next evaluation script based on those files.

Navigate experiments and model registries

The `search_experiments` tool allows Windsurf to discover active project folders and group runs by their actual training targets. This MCP server exposes the entire organization of your machine learning workspace directly to your agent. Once Cascade finds the right experiment, it uses `search_registered_models` to check if that run has been promoted to production. You get a clear view of your staging registry without leaving your code file.

Setup guide

Set up MLflow (ML Lifecycle Management) 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 MLflow (ML Lifecycle Management) 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 MLflow (ML Lifecycle Management) payment history." If connected, Cascade will call the MLflow (ML Lifecycle Management) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "mlflow-ml-lifecycle-management-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 MLflow. 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 MLflow (ML Lifecycle Management) 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 MLflow (ML Lifecycle Management) MCP in Windsurf

Cascade calls `search_runs` to pull your active training sessions directly into your workspace context. It reads the parameters and metrics in real time, allowing you to compare models without leaving your IDE.

Yes, it can. Cascade uses `search_registered_models` to check the current production status of your models and can write the deployment scripts based on those active registry tags.

You add the server config to your `mcp_config.json` file. Once the MCP connection is live, Cascade automatically discovers the tools and starts querying your experiments when you ask about your training runs.

You do not. Cascade uses `search_experiments` and `get_run` to find the exact run IDs itself, pulling the required metrics automatically based on your natural language prompt.

Your training metrics, run parameters, and model artifact paths remain fully inside your secure Vinkius sandbox. The server only transmits metadata to Windsurf locally, meaning your proprietary model weights and training data never leave your infrastructure.

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