How to Use the Coalesce MCP in Google ADK

Q: Can Gemini models analyze Coalesce node schemas using the Google ADK?

Yes. The agent calls listnodes to pull node metadata into Gemini's long-context window, letting it map out complex Snowflake transformations.

Q: How does Google ADK handle errors during a Coalesce run?

When getrunstatus returns a failed state, the agent uses getjobdetails to inspect the error. It can then alert your team via Google Cloud Pub/Sub.

Q: Can I limit which MCP tools my Google agent can execute?

Yes. You can use the toolnames filter in the ADK setup to restrict the agent to read-only tools like listjobs and block write actions like triggerrun.

Let your Google ADK agents manage Coalesce pipelines and connect Snowflake data to your BigQuery and Vertex AI workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Coalesce MCP to Google ADK

Create your Vinkius account to connect Coalesce 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 Coalesce with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Bridge BigQuery and Snowflake via Google ADK

This MCP Server connects your Google ADK agents to Snowflake pipelines for cross-cloud data coordination. Use `list_jobs` to check your Snowflake pipeline status, then trigger BigQuery transfers based on the results. Because the ADK handles long contexts, your agent can analyze hours of job logs at once. It reads the output of `get_job_details` to make smart decisions about downstream Vertex AI training runs.

Analyze complex node metadata with long context

The Coalesce MCP Server exposes deep pipeline architecture schemas directly to your Gemini models. Your agent uses `list_nodes` to pull complete metadata schemas into its massive context window. It maps dependencies across your entire Coalesce environment without running out of memory. This lets the Gemini model plan complex pipeline updates and safety checks before calling `trigger_run`.

Automate cross-cloud pipeline monitoring

This MCP Server lets your Google ADK agents monitor Snowflake transformations before kicking off downstream tasks. Your agent uses `get_run_status` to verify that your Snowflake transformations finished successfully before starting model retraining. If the run fails, the agent queries `get_job_details` to find the exact bottleneck. It logs the failure directly to Google Cloud Logging so your data platform team stays informed.

Setup guide

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

You initialize the McpToolset with your server URL and pass it to your LlmAgent. The agent instantly gains access to tools like `list_environments` to find your target workspaces.

Yes. The agent calls `list_nodes` to pull node metadata into Gemini's long-context window, letting it map out complex Snowflake transformations.

When `get_run_status` returns a failed state, the agent uses `get_job_details` to inspect the error. It can then alert your team via Google Cloud Pub/Sub.

Yes. You can use the tool_names filter in the ADK setup to restrict the agent to read-only tools like `list_jobs` and block write actions like `trigger_run`.

No. Your API key remains securely stored in the Vinkius sandbox. Only clean tool outputs like run statuses and node metadata are passed back to your Google ADK agent.

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