How to Use the Image-Charts MCP in Google ADK

Q: Can Image-Charts handle the high token volume from Google ADK?

Yes, but you should use renderchartpost for heavy datasets. While Gemini can read over one million tokens, the GET tool is limited to 2KB, so the POST tool is necessary for large data structures.

Turn BigQuery data into instant visual dashboards using Gemini and the 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 Image-Charts MCP to Google ADK

Create your Vinkius account to connect Image-Charts 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 Image-Charts with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed BigQuery metrics directly into Image-Charts

The `render_chart_post` tool processes massive datasets extracted from BigQuery by your Gemini agent, converting deep tables into Base64 image URIs. This bypasses the 2KB browser limit, allowing the Google ADK to handle detailed enterprise metrics inside Image-Charts. Because Gemini models have huge context windows, your Google ADK agent can summarize millions of rows first, then pass the aggregated numbers to this Image-Charts tool. The resulting chart gets injected straight into your operational reports via the MCP Server.

Generate fast dashboard links in the Google ADK

The `generate_chart_url` tool creates public-facing image URLs for quick dashboards when your Google ADK visual data fits under the 2KB threshold. This lets your Gemini agent generate lightweight Image-Charts links that load instantly in a browser or chat window. It requires zero Google Cloud storage configuration on your end. The Google ADK agent builds the Image-Charts URL with the correct query parameters, and you can display the output in any web interface immediately.

Map enterprise data to visual tools via the Google ADK

The `generate_chart_url` tool exposes its schema directly to the Google ADK toolset, allowing Gemini to match database columns to chart axes automatically using the MCP standard. You don't need to write custom mapping layers to connect BigQuery to Image-Charts. This speeds up your development loop on Google Cloud. Your Google ADK agent queries Vertex AI, structures the response, and calls the Image-Charts server to output a clean visualization in one single execution step.

Setup guide

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

You define the MCP Server URL inside your streamable HTTP server parameters and pass it to your toolset. The Google ADK exposes the chart generation tools directly to your Gemini agent.

Yes, but you should use `render_chart_post` for heavy datasets. While Gemini can read over one million tokens, the GET tool is limited to 2KB, so the POST tool is necessary for large data structures.

Yes, the framework discovers both tool schemas over the MCP connection automatically. Your agent calls them based on whether it needs a quick link or a raw image payload.

You can use the tool names filter in the ADK toolset configuration. This lets you limit the agent to only use the POST tool over the MCP Server if you want to avoid generating public URLs.

Your enterprise database metrics are transmitted securely to the rendering engine to build the chart and are never saved to disk. The Vinkius sandbox ensures that all data transit is encrypted and completely ephemeral.

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