How to Use the Dynatrace (APM and Observability) MCP in Pydantic AI

Q: How do I initialize the Dynatrace (APM and Observability) toolset in Pydantic AI?

You instantiate the MCPToolset class with your Vinkius HTTP endpoint. Then, pass that toolset directly to your Agent constructor. It takes care of parsing the MCP server's capabilities and exposing them as type-safe Python functions.

Build type-safe observability workflows with Pydantic AI and this Dynatrace 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 Pydantic AI

Create your Vinkius account to connect Dynatrace (APM and Observability) to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate incident data at runtime

The `list_problems` tool fetches active system alerts and passes them directly to your Pydantic AI agent over MCP. The framework validates every field against strict Python types, preventing malformed payloads from breaking your pipeline. If you need to dive deeper, `get_problem` provides detailed root-cause analysis. Because every field matches your Pydantic models, you can safely write logic to auto-close resolved alerts using `close_problem`.

Query metrics with zero type errors

The `query_metrics` tool retrieves raw performance data points for your infrastructure. Pydantic AI ensures the returned timestamps and floats match your expected schemas before your code processes them. If you need to push custom metrics, `ingest_metrics` lets you write data points back to your dashboard. This strict validation prevents corrupt data from polluting your production databases.

Manage account access safely

The `list_account_users` tool retrieves the list of active users in your Dynatrace account. Your agent can cross-reference this list with your internal directory to find stale accounts. To fix access issues, the agent uses `update_account_group_permissions` to adjust user rights. Every permission change is validated against your Pydantic schemas before the API call executes.

Setup guide

Set up Dynatrace (APM and Observability) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "dynatrace-apm-and-observability-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Dynatrace (APM and Observability) tools.",
)

result = await agent.run("List recent Dynatrace (APM and Observability) transactions")
print(result.output)

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 Pydantic AI

If the API structure changes, the framework will raise a validation error immediately instead of failing silently. This ensures your agent never processes corrupt data from tools like `list_problems`. It makes your observability pipeline incredibly resilient to upstream updates.

Yes, the framework is completely model-agnostic. You can connect local LLMs or commercial APIs to the MCP server and get the same strict type safety. This is ideal for teams running private infrastructure.

You instantiate the `MCPToolset` class with your Vinkius HTTP endpoint. Then, pass that toolset directly to your Agent constructor. It takes care of parsing the MCP server's capabilities and exposing them as type-safe Python functions.

Yes, the framework is built from the ground up for async Python. You can query metrics and check problems concurrently without blocking your main execution thread.

Your data remains entirely within your local Python runtime and the secure Vinkius gateway. We use end-to-end encryption for all API traffic, and our infrastructure does not write any telemetry payload to disk. Only the raw connection token is validated at the edge.

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