How to Use the Datadog MCP in Google ADK

Q: Can Google ADK filter which MCP tools the agent sees?

Yes. You pass a toolnames array to the toolset initialization. This restricts the agent to specific actions like listhosts or listslos.

Give your Google ADK agents an MCP Server to read Datadog telemetry and reason across millions of tokens.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Datadog MCP to Google ADK

Create your Vinkius account to connect Datadog 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 Datadog with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed logs into Gemini

Enterprise observability generates a massive amount of text. Gemini models thrive on huge context windows, making them perfect for analyzing hours of system output. Your agent runs `search_logs` to pull thousands of lines of application errors. It dumps that entire payload into the context window to spot patterns across your GCP infrastructure.

Bridge telemetry and data warehouses

Siloed data slows down root cause analysis. Connecting your observability platform to Google's ecosystem lets you cross-reference active alerts with historical business data. The agent calls `list_metrics` and `query_metrics` to grab real-time performance stats. It then correlates those numbers with BigQuery tables to see if a traffic spike impacted revenue.

Control this Datadog MCP Server

You do not always want an agent having full access to your alerting rules. Google ADK lets you restrict exactly which operations your bots can touch. By applying a tool_names filter to the McpToolset, you expose `list_monitors` and `search_monitors` while blocking `mute_monitor`. Your agent gets read-only visibility without the risk of silencing critical alerts.

Setup guide

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

Install google-adk from pip. Create an McpToolset using StreamableHttpServerParameters with your Vinkius URL, then pass it to the tools list in your LlmAgent.

Yes. You pass a tool_names array to the toolset initialization. This restricts the agent to specific actions like list_hosts or list_slos.

It does. The framework supports both Stdio and HTTP transports. Vinkius provides a managed HTTP endpoint so you skip the local server setup.

Gemini models support contexts of over one million tokens. You pull extensive historical data via search_logs and the agent processes it in a single prompt.

We handle your infrastructure data entirely in memory. The connection authenticates via a single endpoint token, and the V8 isolate containing your hostname lists gets destroyed immediately after the response.

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