How to Use the Deno Deploy MCP in Google ADK

Q: Can Google ADK filter Deno Deploy tools?

The framework supports a toolnames parameter. You restrict the agent to read-only operations like getorganization.

Q: Does Google ADK handle Deno Deploy build logs?

Gemini ingests the output from getbuildlogs perfectly. Its long-context reasoning parses massive stack traces without dropping details.

Connect Deno Deploy to Google ADK. Let Gemini manage your edge applications and analyze build logs with massive context windows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deno Deploy MCP to Google ADK

Create your Vinkius account to connect Deno Deploy 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 Deno Deploy with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Gemini-Powered Infrastructure via MCP Server

Feeding output from `get_app_logs` into Gemini changes how you debug edge apps. Feed an entire week of logs directly into the model. It actually remembers the entire trace and finds the exact regression causing your downtime. Pushing fixes is just as direct. Your agent triggers `create_deployment` to ship the corrected code immediately. Using the McpToolset class bridges the gap between Google Cloud and your edge environments via our managed MCP connection.

Filtered Tool Access

Restricting tools like `list_apps` using Google ADK filters prevents enterprise agents from having god mode. You can restrict the toolset using the tool_names parameter. Give an agent access to read logs, but block it from creating new projects entirely. This limits the blast radius of any autonomous script. If you only want an observability agent, expose `get_build_logs` and nothing else. The Vinkius endpoint handles the required authentication automatically.

Cross-Cloud Intelligence

Scheduling an agent to pull `get_app` metrics moves your edge data directly into BigQuery. A scheduled task formats the infrastructure stats for your data warehouse. You get a complete view of your Deno Deploy usage right inside Vertex AI. Environment variables sync up through `update_layer`. The system reads your Google Secret Manager and updates the edge configuration to match. Everything runs through a simple HTTP transport layer to the MCP Server.

Setup guide

Set up Deno Deploy 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 Deno Deploy 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="Deno Deploy_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Deno Deploy 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 Deno Deploy. 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 Deno Deploy 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 Deno Deploy MCP in Google ADK

Pass the Vinkius URL into StreamableHttpServerParameters. Wrap that in McpToolset and hand it to your LlmAgent.

The framework supports a tool_names parameter. You restrict the agent to read-only operations like `get_organization`.

Gemini ingests the output from `get_build_logs` perfectly. Its long-context reasoning parses massive stack traces without dropping details.

We recommend the HTTP transport for cloud deployments. The Vinkius zero-trust architecture requires just one endpoint token to connect.

Your list of domains, project details, and source code deployments remain strictly between your Google Cloud setup and the API. Our Vinkius sandbox executes the request and immediately destroys the memory state.

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