How to Use the Comet ML MCP in Google ADK

Q: Can I filter which Comet ML tools are exposed to the Google ADK?

Yes. Use the toolnames filter in your McpToolset configuration to restrict access to specific tools like getexperimentmetrics.

Q: How does the Google ADK handle long Comet ML experiment lists?

Gemini's long context handles large arrays returned by listexperiments easily. The agent reads thousands of runs without hitting token limits.

Q: Can my Google ADK agent write Comet ML metrics to BigQuery?

Yes. The agent can fetch numeric bounds using getexperimentmetrics and write them directly into BigQuery tables.

Run enterprise-scale Comet ML audits inside the Google ADK with this MCP Server using Gemini's million-token context.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Comet ML MCP to Google ADK

Create your Vinkius account to connect Comet ML 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 Comet ML with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Comet ML workspaces directly into Gemini context

Use `list_workspaces` to pull your entire Headless Comet organization structure into the Google ADK context window. Gemini can analyze thousands of active workspaces at once without running out of memory. The agent identifies workspace limits and pairs them with your BigQuery data. This lets you run massive audits across all your active enterprise projects in one go.

Query experiment parameters using Google ADK tools

This MCP Server lets your Gemini agent call `get_experiment_params` to inspect taxonomy types. You can compare these parameters against Vertex AI model deployments to ensure consistency. The agent extracts the properties and writes them to your Google Cloud logs. No manual copy-pasting between your training runs and your cloud infrastructure.

Match BigQuery datasets with Comet ML projects

This MCP Server lets you call `list_projects` from your Google ADK agent to match your raw data tables in BigQuery with active training runs. The agent checks that your training inputs match the registered project names. If there is a mismatch, the agent alerts your team. This keeps your training pipelines tied to the correct data warehouse sources.

Setup guide

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

Yes. Use the tool_names filter in your McpToolset configuration to restrict access to specific tools like get_experiment_metrics.

Gemini's long context handles large arrays returned by list_experiments easily. The agent reads thousands of runs without hitting token limits.

Yes. You can connect this MCP Server using either transport method depending on whether your agent runs locally or on Google Cloud.

Yes. The agent can fetch numeric bounds using get_experiment_metrics and write them directly into BigQuery tables.

Connection tokens are managed securely in Vinkius. Your logged metrics and run parameters are transmitted over HTTPS directly to your Google Cloud environment.

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