How to Use the GridStatus MCP in Google ADK

Q: How do I check my remaining query quota?

Your agent can call getapiusage at the start of a workflow. This returns your current row usage and remaining allowance, letting you manage costs programmatically.

Run enterprise energy agents in Google ADK using real-time GridStatus data and Gemini's massive context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GridStatus MCP to Google ADK

Create your Vinkius account to connect GridStatus 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 GridStatus with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject GridStatus Datasets into BigQuery Pipelines

Pipe live grid metrics directly into your Google Cloud data warehouse. Your agent uses `query_dataset` to pull historical electricity data and format it for BigQuery. This lets you combine weather models with actual grid load. The Google ADK toolset handles the heavy lifting of connecting the MCP Server to Vertex AI. Your agent can scan years of historical grid patterns in a single prompt using Gemini's million-token context window.

Automate Regional Power Market Analysis

Evaluate wholesale price differences across different US grids. Your agent queries `get_lmp_data` to pull day-ahead locational marginal pricing for CAISO, PJM, or NYISO. It identifies congestion points by comparing nodal prices. For Texas markets, the agent calls `get_spp_data` to fetch day-ahead hourly settlement point prices. It maps these regional pricing trends against industrial load centers to optimize your regional power procurement.

Monitor Fuel Mix Changes on Google ADK

Track the real-time share of renewables in the generation mix. Your agent uses `get_fuel_mix` to see how wind and solar output affects wholesale pricing. This provides clean data for environmental compliance reporting. Before pulling massive datasets, your agent runs `list_datasets` to see what tables are available. It verifies date ranges and columns using `get_dataset_metadata` to avoid running redundant queries that waste API credits.

Setup guide

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

Import McpToolset from the SDK and point it to your Vinkius MCP endpoint. Pass this toolset to your agent constructor to give Gemini immediate access to all grid tools.

Yes. Gemini can analyze massive historical datasets retrieved via `query_dataset` alongside real-time load from `get_load_data`. Its long-context window allows it to find correlations across multiple months of grid events.

You can use the optional tool name filter when defining your McpToolset. This restricts the MCP tools exposed to the agent, letting you lock down configuration tools while keeping pricing tools open.

Your agent can call `get_api_usage` at the start of a workflow. This returns your current row usage and remaining allowance, letting you manage costs programmatically.

Yes. The MCP Server only retrieves public electricity grid data such as fuel mix, load, and capacity metrics. Your Google Cloud credentials and private API keys are never exposed, and all tool execution occurs in secure, ephemeral sandboxes.

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