How to Use the EyePop.ai MCP in Google ADK

Q: Can Gemini analyze video files directly using EyePop.ai and Google ADK?

Gemini coordinates the process by calling analyzevideo through the toolset. The tool returns temporal detection data, which Gemini then parses and explains.

Q: How does the long context of Gemini benefit from these vision tools?

The output from listdetections can be highly detailed. Gemini's million-token context easily digests these large JSON payloads to summarize long-term patterns in your visual data.

Q: Where are my analyzed images and video files stored during processing?

All media processed via analyzeimage is handled in an ephemeral sandbox. Vinkius ensures your visual data is processed in-memory and discarded immediately after the MCP execution completes.

Feed computer vision data directly into your Gemini models using the Google ADK and EyePop.ai.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EyePop.ai MCP to Google ADK

Create your Vinkius account to connect EyePop.ai 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 EyePop.ai with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run the EyePop.ai MCP Server with Gemini

Pass raw media to Gemini and let it run `analyze_image` or `analyze_video` to extract structured bounding boxes. This tool integration lets your agent process visual feeds and feed the resulting JSON coordinates directly into its reasoning loop. Because Google ADK supports massive context windows, you can dump large detection payloads from `list_detections` straight into Gemini. The model can then analyze trends across hours of footage without running out of memory.

Cloud-Native Visual Pipeline Management

Connect your visual data pipelines with Google Cloud infrastructure using `create_pop` to configure a new analysis pipeline. Your agent can then store the output metadata directly in BigQuery for long-term analytics. Use `get_pop` or `list_pops` to check which active configurations match your Vertex AI model deployments. This creates a clean bridge between your custom cloud models and ready-to-use vision pipelines.

Dynamic Model Inventory Audits

Let your Gemini agents dynamically check available vision models using `list_models` and `get_model`. If a specific classification model is missing, the agent can alert your team or choose an alternative path. Run `check_eyepop_status` as a startup check inside your cloud functions. This ensures your agent has a clear path to the MCP backend before attempting heavy processing tasks.

Setup guide

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

Use McpToolset with the Vinkius HTTP server parameters. Pass this toolset into your LlmAgent instance to expose the vision tools to Gemini.

Gemini coordinates the process by calling `analyze_video` through the toolset. The tool returns temporal detection data, which Gemini then parses and explains.

Yes. You can pass a filtered list of tool names to the McpToolset constructor to limit the agent's access to specific tools like `analyze_image`.

The output from `list_detections` can be highly detailed. Gemini's million-token context easily digests these large JSON payloads to summarize long-term patterns in your visual data.

All media processed via `analyze_image` is handled in an ephemeral sandbox. Vinkius ensures your visual data is processed in-memory and discarded immediately after the MCP execution completes.

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