How to Use the Dynatrace (APM and Observability) MCP in Google ADK

Q: How does the Google ADK execute Dynatrace (APM and Observability) tools?

The framework uses the McpToolset class to connect directly to the hosted MCP server. Gemini discovers the available tools and executes them dynamically when answering user queries. This lets you combine observability data with Vertex AI models out of the box.

Q: Can I use Gemini's long context with Dynatrace (APM and Observability) data in Google ADK?

Yes, you can feed thousands of metrics from querymetrics directly into Gemini. The model handles massive datasets easily, allowing it to spot complex patterns that shorter-context models miss. This is perfect for analyzing massive distributed systems.

Feed live Dynatrace telemetry directly into Gemini's 1M-token context window using the Google ADK 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 Dynatrace (APM and Observability) MCP to Google ADK

Create your Vinkius account to connect Dynatrace (APM and Observability) 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 Dynatrace (APM and Observability) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze long-term system health

The `list_events` tool retrieves historical performance alerts and state changes over long timeframes. Gemini uses its massive context window to correlate these events with your BigQuery database logs. By comparing these logs with `list_problems`, the agent identifies systemic platform weaknesses. It then writes these findings directly into a new dashboard using `create_dashboard`.

Map your entire cloud environment

The `list_entities` tool pulls the complete list of monitored hosts, services, and applications from your environment using this MCP Server. Your agent analyzes these relationships to map dependencies across your Google Cloud infrastructure. To drill down, the agent uses `list_entity_types` to categorize untagged resources. This allows the model to spot unmonitored services and flag them for your platform engineering team.

Automate synthetic test suites

The `list_synthetic_monitors` tool lists all active synthetic tests running across your global locations. Your agent checks this list to ensure critical user journeys are covered. If an endpoint degrades, the agent updates the test configuration using `update_synthetic_monitor`. This keeps your testing suite aligned with live application updates.

Setup guide

Set up Dynatrace (APM and Observability) 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 Dynatrace (APM and Observability) 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="Dynatrace (APM and Observability)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Dynatrace (APM and Observability) 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 Dynatrace. 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 Dynatrace (APM and Observability) 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 Dynatrace (APM and Observability) MCP in Google ADK

The framework uses the `McpToolset` class to connect directly to the hosted MCP server. Gemini discovers the available tools and executes them dynamically when answering user queries. This lets you combine observability data with Vertex AI models out of the box.

Yes, you can feed thousands of metrics from `query_metrics` directly into Gemini. The model handles massive datasets easily, allowing it to spot complex patterns that shorter-context models miss. This is perfect for analyzing massive distributed systems.

Yes, you can pass a specific list of tool names to the toolset parameter in your Python script. This limits the agent's access to safe operations like `list_problems` while hiding administrative actions. It gives you total control over what the model can execute.

You can write a custom tool in Google ADK that queries BigQuery, then pass both that tool and the Dynatrace toolset to your agent. The model will naturally use both sources to resolve complex performance issues.

All data retrieved from your environment is transmitted over TLS 1.3 directly to your Google Cloud environment. Vinkius acts as a stateless proxy for the MCP connection, meaning no telemetry or configuration data is ever stored on our servers. Your API tokens are managed via secure environment variables.

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