How to Use the Curve Fitting Engine MCP in Google ADK

Q: How do I connect the Curve Fitting Engine to my Google ADK agent?

After installing the google-adk package, you create an McpToolset instance, pointing it to your Vinkius server URL. Then you pass that toolset into the LlmAgent constructor's tools list.

Q: Can I filter which tools from an MCP Server my agent sees?

Yes, the McpToolset in the Google ADK has an optional toolnames filter. This lets you expose only specific tools to an agent, even if the server offers more.

Connect your Google ADK agent to BigQuery data for instant, precise polynomial regression analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Curve Fitting Engine MCP to Google ADK

Create your Vinkius account to connect Curve Fitting 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 Curve Fitting Engine with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Regressions on BigQuery Data

Give your Google ADK agent the `calculate_regression` tool. It can now pull a dataset directly from a BigQuery table, summarize it, and then run a precise polynomial regression to find the trendline. This connects your agent's reasoning ability directly to your data warehouse. It's not just talking about the data; it's performing real calculations on it. The agent can find a correlation and immediately prove it with a mathematical fit.

Long-Context Analysis with Your MCP Server

Load a massive report into a Gemini 1.5 Pro context window. Your agent can discuss the data with you, identify key columns for analysis, and then use this MCP Server to fit a curve to that specific data. The agent doesn't lose track. It can hold the entire conversation and the data's structure in its head, then call the `calculate_regression` tool for a specific task. This works great for exploratory data analysis.

A Deterministic Tool for Your Agent

An LLM on its own can't perform true regression. It approximates. This tool gives your Gemini agent a sharp, reliable instrument for one specific job: curve fitting. The results are always the same for the same data. By adding this MCP toolset, you're augmenting the agent with a skill it doesn't have. It offloads the hard math to a specialized service, and your agent just focuses on when and why to use it.

Setup guide

Set up Curve Fitting 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 Curve Fitting 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="Curve Fitting Engine_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Curve Fitting 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 ml-regression. 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 Curve Fitting 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 Curve Fitting Engine MCP in Google ADK

After installing the `google-adk` package, you create an `McpToolset` instance, pointing it to your Vinkius server URL. Then you pass that toolset into the `LlmAgent` constructor's `tools` list.

Yes, the `McpToolset` in the Google ADK has an optional `tool_names` filter. This lets you expose only specific tools to an agent, even if the server offers more.

Absolutely. It's a perfect fit. Your Google ADK agent can query and reason over data in BigQuery, then use the Curve Fitting Engine to perform precise mathematical analysis on subsets of that data.

Gemini will describe a trend qualitatively or attempt an approximation. The Curve Fitting Engine performs an exact, deterministic mathematical calculation, returning a precise equation and R-squared score that you can actually use.

The scatter plot data you send is handled exclusively by the Vinkius MCP endpoint. It's processed in an isolated sandbox and never written to disk. This process is entirely separate from your Google Cloud environment.

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