How to Use the Fundamental Math MCP in Google ADK

Q: How do I connect the Fundamental Math tools to Google ADK?

Install google-adk via pip. Wrap the Vinkius endpoint in a McpToolset using StreamableHttpServerParameters. Then pass that toolset directly into your LlmAgent configuration.

Q: Can I restrict which Fundamental Math tools my Google ADK agent sees?

Yes. You can use the toolnames filter in the SDK to hide specific functions. If you only want the agent to use calculateruleofthree, simply filter out the rest.

Give your Google ADK agents local, exact calculation tools to process massive BigQuery datasets without hallucinated numbers.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fundamental Math MCP to Google ADK

Create your Vinkius account to connect Fundamental Math 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 Fundamental Math with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Exact math for BigQuery agents

Gemini models hold millions of tokens, but they still struggle with exact arithmetic. When your Google ADK agent pulls a massive financial report from BigQuery, you need deterministic math to analyze it. This MCP Server gives your agent native tools to handle the numbers. Instead of prompting the model to guess a proportion, the agent calls `calculate_rule_of_three`. The calculation runs locally and returns a guaranteed exact floating-point result. Your enterprise data stays accurate across the entire pipeline.

Filtered toolsets in Google ADK

You rarely want an agent to have access to every tool at once. Google ADK lets you restrict the exposed operations using the `tool_names` filter. If your current task only requires finding square roots, you can limit the agent to just `calculate_square_root`. This prevents the model from getting distracted by irrelevant functions. By isolating `calculate_percentage` for a tax calculation agent, you reduce token overhead and keep the execution path strictly focused on the math that matters.

Zero-latency local execution

Relying on cloud APIs for basic arithmetic creates massive bottlenecks. If your agent is iterating through thousands of Vertex AI records, waiting for a network response on every math operation will kill your performance. We built these tools to execute with zero latency. When the agent triggers `calculate_factorial` or `calculate_power`, the computation happens instantly on the local machine. You get the speed of native code with the reasoning power of Gemini.

Setup guide

Set up Fundamental Math 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 Fundamental Math 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="Fundamental Math_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Fundamental Math 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 math-fundamental. 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 Fundamental Math 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 Fundamental Math MCP in Google ADK

Install `google-adk` via pip. Wrap the Vinkius endpoint in a `McpToolset` using `StreamableHttpServerParameters`. Then pass that toolset directly into your `LlmAgent` configuration.

Running arbitrary eval on LLM outputs is a massive security risk. This MCP Server restricts the agent to exactly five safe operations, like `calculate_power` and `calculate_percentage`, preventing malicious code injection.

Yes. You can use the `tool_names` filter in the SDK to hide specific functions. If you only want the agent to use `calculate_rule_of_three`, simply filter out the rest.

It does. You can load a massive dataset into the context window and instruct the agent to run `calculate_square_root` on specific extracted values. The math executes locally and feeds the exact answers back into the prompt.

We operate a zero-trust architecture. When your Gemini agent sends integers or floats to the server, they process inside a locked-down V8 isolate. The sandbox dies the millisecond the calculation finishes, leaving zero trace of your data.

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