How to Use the DVC MCP in Google ADK

Q: Can Google ADK agents filter specific DVC views?

Yes. The agent uses listviews to find all available data slices and then runs getview to inspect the metadata of the chosen slice. This lets the agent select the right dataset for Vertex AI training.

Q: How does Google ADK handle large payloads from DVC?

Gemini models handle massive contexts easily. When listexperiments returns a long list of runs, the ADK feeds the raw JSON directly into the model without needing aggressive truncation.

Feed deep DVC experiment history into Gemini's massive context window using Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DVC MCP to Google ADK

Create your Vinkius account to connect DVC 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 DVC with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze huge experiment histories via Google ADK

The `list_experiments` tool feeds your entire DVC training history into Gemini's long-context window via Google ADK. Your Google ADK agent reads hundreds of DVC runs at once to find patterns that humans miss. It checks parameters against final loss metrics to suggest your next hyperparameter tuning steps. This DVC MCP integration bypasses the usual token limits of standard models by feeding raw run data straight to Gemini. You'll pull massive tables of DVC runs and let the Google ADK agent reason over the entire project history in a single turn.

Align cloud data with DVC MCP Server views

Use `get_view` and `list_views` to connect your Vertex AI datasets with DVC tracking via Google ADK. The Google ADK agent checks the active DVC view version, matches it with your BigQuery source, and ensures your training run uses the correct data split. Because Google ADK handles cloud-native tools, your agent can write the results of these DVC checks back to your Google Cloud logging system. You get a unified view of your DVC data lineage.

Audit team projects across Google Cloud

The `list_projects` and `get_project` tools let your Google ADK agent index your active DVC ML repositories using our MCP endpoint. The Google ADK agent maps out your team's workspace structure and identifies stale DVC experiments. By calling `get_user` on DVC run owners, the Google ADK agent can send alerts when a run fails. It's a quick way to automate the tedious parts of team coordination across your DVC projects.

Setup guide

Set up DVC 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 DVC 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="DVC_agent",
    model="gemini-2.0-flash",
    instruction="You have access to DVC 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 DVC. 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 DVC 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 DVC MCP in Google ADK

Install the ADK package and configure the HTTP server parameters with your Vinkius token. Pass the toolset directly to your LlmAgent instance. The agent will auto-discover tools like `list_experiments`.

Yes. The agent uses `list_views` to find all available data slices and then runs `get_view` to inspect the metadata of the chosen slice. This lets the agent select the right dataset for Vertex AI training.

Gemini models handle massive contexts easily. When `list_experiments` returns a long list of runs, the ADK feeds the raw JSON directly into the model without needing aggressive truncation.

You can pass a tool name filter when initializing your toolset. This lets you expose only read-only tools like `list_projects` while hiding administrative actions.

All MCP metadata remains inside your secure Google Cloud perimeter and the Vinkius sandbox. We do not persist your project structures or user profiles on external databases.

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