How to Use the Neptune.ai (ML Experiment Tracking) MCP in Google ADK

Q: How can Google ADK find the best-performing run in my Neptune.ai (ML Experiment Tracking) project?

Your Gemini agent uses the searchruns tool with a query to sort by your main metric, like 'accuracy' descending. It gets the top run ID, then uses getattributes to pull all its parameters for your review.

Q: How do I manage multiple Neptune projects with a single agent using this MCP toolset?

The listprojects tool gives your agent a list of all accessible projects. You can then prompt it to focus on a specific one by name, which it will use in subsequent calls to searchruns.

Let your Gemini agent on Google ADK query Neptune.ai experiments and connect insights to your Google Cloud data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Neptune.ai (ML Experiment Tracking) MCP to Google ADK

Create your Vinkius account to connect Neptune.ai (ML Experiment Tracking) to Google ADK 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 Neptune.ai (ML Experiment Tracking) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Runs from Your Gemini Agent

Give your Gemini agent access to your entire Neptune.ai experiment history. Gemini's massive context window means you can pull data from dozens of runs using `search_runs` and have the agent reason over all of it at once. It can find trends and outliers that would be tedious to spot manually. This is great for complex questions. Ask your agent to find all runs with an F1 score above 0.9 and then identify the common hyperparameters. It uses `get_attributes` on each result and synthesizes a single, coherent answer.

Connect Neptune Metrics to BigQuery

This is where things get interesting. Your Google ADK agent can act as a bridge between your ML experiments and your data warehouse. It can use `get_attributes` to pull key metrics from a finished Neptune.ai run, then immediately use another tool to insert that data into a BigQuery table. This closes the loop between training and long-term analysis. You can build automated reporting systems where a Gemini agent monitors Neptune.ai, extracts performance data from new models, and populates your Google Cloud dashboards without any human intervention.

Enterprise-Ready MCP Server Integration

Setting this up fits right into your existing Google Cloud workflow. After installing the ADK, you create an `McpToolset` pointing to the server URL. This toolset plugs directly into your `LlmAgent` instance alongside any other Google Cloud tools you're using. For more control, you can use the `tool_names` filter when creating the toolset. This lets you expose only specific functions, like `search_runs`, to a particular agent. It's a simple way to enforce permissions and build specialized agents for different MLOps tasks.

Setup guide

Set up Neptune.ai (ML Experiment Tracking) MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Neptune.ai (ML Experiment Tracking) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Neptune.ai (ML Experiment Tracking)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Neptune.ai (ML Experiment Tracking) tools via MCP.",
    tools=mcp_tools,
)

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 Neptune.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 Neptune.ai (ML Experiment Tracking) 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 Neptune.ai (ML Experiment Tracking) MCP in Google ADK

Your Gemini agent uses the `search_runs` tool with a query to sort by your main metric, like 'accuracy' descending. It gets the top run ID, then uses `get_attributes` to pull all its parameters for your review.

Absolutely. Your agent can query Neptune.ai for model metadata using `list_models` and `get_attributes`. It can then use that information to trigger a Vertex AI pipeline, passing the model's location or parameters as arguments.

It's built for the Google Cloud ecosystem. If your data is in BigQuery or you use Vertex AI for pipelines, your agent becomes the glue. It pulls experiment data from Neptune.ai and uses it directly with your other Google services.

The `list_projects` tool gives your agent a list of all accessible projects. You can then prompt it to focus on a specific one by name, which it will use in subsequent calls to `search_runs`.

This MCP server only reads your Neptune.ai metadata, such as run parameters and metrics, and never modifies anything. Each request is handled in an isolated, single-use environment on Vinkius, meaning your data isn't stored or logged beyond that transaction.

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