$Infracost logo$

How to Use the Infracost MCP in Google ADK

Q: How do I register the Infracost MCP Server within a Google ADK agent?

Initialize McpToolset with your Vinkius HTTP endpoint parameter. Pass this toolset instance inside the tools list when instantiating your LlmAgent.

Q: Can Gemini models use Infracost to automatically fix tag violations?

Yes, the agent calls updatetaggingpolicy to define correct tags. It then reconciles resource tags against your BigQuery assets to fix non-compliant infrastructure.

Q: How do I handle large CSV price books with Infracost and Google ADK?

Your agent uses getpricebookfilesurl to get a presigned URL, uploads the file, and triggers ingestpricebook. This offloads heavy file processing from your Gemini execution context.

Feed Infracost cloud cost limits directly into your Gemini-powered enterprise agents using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

$Infracost MCP on Cursor AI Code Editor MCP Client$ $Infracost MCP on Claude Desktop App MCP Integration$ $Infracost MCP on OpenAI Agents SDK MCP Compatible$ $Infracost MCP on Visual Studio Code MCP Extension Client$ $Infracost MCP on GitHub Copilot AI Agent MCP Integration$ $Infracost MCP on Google Gemini AI MCP Integration$ $Infracost MCP on Lovable AI Development MCP Client$ $Infracost MCP on Mistral AI Agents MCP Compatible$ $Infracost MCP on Amazon AWS Bedrock MCP Support$

MCP Servers - Free for Subscribers

Connect Infracost MCP to Google ADK

Create your Vinkius account to connect Infracost 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 Infracost with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query actual cloud rates via Google ADK

The `query_pricing` tool fetches raw pricing data using GraphQL queries to feed your Gemini models. Your agent parses this data to calculate the exact cost of spinning up new Google Cloud or multi-cloud resources. Because the Google ADK handles long-context reasoning with Gemini's 1M+ token window, you can feed entire pricing catalogs into a single prompt. The agent matches these against BigQuery billing logs to find discrepancies.

Run enterprise price book ingestion in GCP

The `ingest_price_book` tool processes your custom enterprise discount CSVs directly from your Gemini workflows. Your agent requests a secure upload endpoint via `get_price_book_files_url` and monitors the processing status using `get_price_book`. This Google ADK toolset setup allows you to filter which operations are exposed by using the `tool_names` parameter. Once the custom rates are processed, your agent uses `update_organization` to apply these rates across your enterprise profile.

Guardrail management through this MCP Server

The `create_guardrail` tool defines budget thresholds that your Gemini agents must respect before approving any cloud infrastructure. Your agent can modify or remove these rules dynamically using `update_guardrail` and `delete_guardrail`. This integration runs over either Stdio or HTTP transports within your Google Cloud environment. It gives your automated deployment pipelines a hard financial gate, preventing runaway costs before they hit your monthly bill.

Setup guide

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

Initialize `McpToolset` with your Vinkius HTTP endpoint parameter. Pass this toolset instance inside the `tools` list when instantiating your `LlmAgent`.

Yes, the agent calls `update_tagging_policy` to define correct tags. It then reconciles resource tags against your BigQuery assets to fix non-compliant infrastructure.

Yes, all tools are exposed by default. You can restrict access to specific tools like `delete_guardrail` by configuring the `tool_names` filter in your toolset parameters.

Your agent uses `get_price_book_files_url` to get a presigned URL, uploads the file, and triggers `ingest_price_book`. This offloads heavy file processing from your Gemini execution context.

The CSV data containing your custom contract rates is sent over an encrypted HTTPS connection directly to the sandboxed Vinkius execution environment. It is never stored or used to train Gemini models.

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