How to Use the Moving Average Engine MCP in Google ADK

Q: How do I configure the Moving Average Engine in Google ADK?

Create a StreamableHttpServerParameters instance with your server URL. Wrap that in an McpToolset and pass it to the tools array when defining your LlmAgent.

Run exact financial calculations on massive BigQuery datasets 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 Moving Average Engine MCP to Google ADK

Create your Vinkius account to connect Moving Average Engine 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 Moving Average Engine with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stop Gemini from guessing math

The `calculate_moving_average` tool computes exact Simple (SMA) and Exponential (EMA) values from numerical arrays. Gemini models have massive 1M+ token context windows, which is great for ingesting historical data but terrible for performing recursive arithmetic on it. This MCP Server forces the agent to use a deterministic calculator. You pass your `McpToolset` directly into your `LlmAgent` configuration. When the agent pulls raw time-series data from BigQuery, it routes the arrays to this external engine. The resulting trend lines are mathematically flawless, ready for enterprise dashboards or automated reporting.

Native Google Cloud integration

The `calculate_moving_average` tool hooks directly into your existing Google Cloud infrastructure. You instantiate the connection using `StreamableHttpServerParameters` and wrap it in the standard toolset. The agent framework handles the network transport natively. Enterprise deployments often require strict control over what an agent can do. You can use the `tool_names` filter in the ADK to restrict access, ensuring only authorized specialized agents can trigger the calculation. This keeps your architecture modular and secure.

Managed MCP Server reliability

The `calculate_moving_average` tool runs on Vinkius infrastructure, removing the need to host custom Python math APIs. You get a single endpoint token and plug it into the ADK. The server handles the array reduction and division logic instantly. Building financial agents requires trusting the underlying math. By offloading deterministic operations to a dedicated MCP architecture, you free up Gemini to do what it does best: reason about the results. The technical indicators come back exact every single time.

Setup guide

Set up Moving Average Engine 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 Moving Average Engine 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="Moving Average Engine_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Moving Average Engine 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 technicalindicators. 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 Moving Average Engine 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 Moving Average Engine MCP in Google ADK

Create a `StreamableHttpServerParameters` instance with your server URL. Wrap that in an `McpToolset` and pass it to the `tools` array when defining your `LlmAgent`.

Yes. Your agent can query BigQuery for historical price data, extract the numerical arrays, and pass them directly to the moving average tool. The engine calculates the indicators and returns them to the agent.

Foundation models are probabilistic text generators, not calculators. They routinely fail at recursive floating-point math. Offloading this to a dedicated engine guarantees mathematical exactness.

No. The server strictly computes Simple Moving Averages (SMA) and Exponential Moving Averages (EMA). It does exactly one thing with absolute precision.

The isolated environment processes your numerical inputs in memory and shuts down immediately after returning the calculation. Nothing is written to disk. The ephemeral architecture guarantees your proprietary trading data never leaks.

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