How to Use the Modal (Serverless AI Infrastructure) MCP in Google ADK

Q: Can I use Google ADK to manage Modal (Serverless AI Infrastructure) deployments?

Yes, you pass the McpToolset pointing to the Vinkius HTTP URL into your LlmAgent. The agent immediately gains access to tools like listdeployments over the MCP link.

Q: Can I limit which tools Google ADK can access on Modal (Serverless AI Infrastructure)?

You can use the optional toolnames filter during initialization to restrict access. For example, you can run this MCP setup with strict permissions, exposing only getapp while blocking destructive tools.

Connect Gemini long-context reasoning with your GPU infrastructure using the Google ADK and our managed MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Modal (Serverless AI Infrastructure) MCP to Google ADK

Create your Vinkius account to connect Modal (Serverless AI Infrastructure) 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 Modal (Serverless AI Infrastructure) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query active serverless apps using Google ADK

The `list_apps` tool provides a complete inventory of your active and historical serverless runtimes. Your Gemini model processes this entire context window to correlate execution patterns with your BigQuery operational logs. Enterprise agents use this data to identify failing runs without manual terminal checks. The framework maps the JSON output directly into your agent's working memory.

Coordinate network storage with Gemini reasoning

This MCP Server lists your persistent network block volumes to verify storage mounts before starting heavy training runs. Gemini reads the volume metadata to ensure your training data partitions are mapped correctly. You avoid empty-mount failures that waste expensive GPU hours by checking these mounts first. Direct pipelines connect your GCP storage planning straight to your serverless execution layer.

Track live production deployments

The `get_deployment` tool fetches the exact specifications of your active serverless endpoints. Gemini uses these details to match your Vertex AI routing rules with actual running containers. If a deployment drops, the agent uses `list_deployments` to find a healthy fallback. You build self-healing infrastructure loops without writing custom bash scripts.

Setup guide

Set up Modal (Serverless AI Infrastructure) 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 Modal (Serverless AI Infrastructure) 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="Modal (Serverless AI Infrastructure)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Modal (Serverless AI Infrastructure) 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 Modal. 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 Modal (Serverless AI Infrastructure) 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 Modal (Serverless AI Infrastructure) MCP in Google ADK

Yes, you pass the `McpToolset` pointing to the Vinkius HTTP URL into your `LlmAgent`. The agent immediately gains access to tools like `list_deployments` over the MCP link.

Gemini's million-token context window easily digests the complete history returned by `list_apps`. The model analyzes hours of deployment logs without running out of memory.

You can use the optional tool_names filter during initialization to restrict access. For example, you can run this MCP setup with strict permissions, exposing only `get_app` while blocking destructive tools.

Your agent queries BigQuery for training targets, then verifies the target storage with `list_volumes`. This connects your data warehouse to your compute cluster.

The server only queries the platform's API for app statuses and volume names. All communication uses ephemeral V8 sandboxes that wipe your credentials immediately after execution.

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