How to Use the Datadog AI (LLM Observability) MCP in Pydantic AI

Q: Does Pydantic AI support Datadog AI (LLM Observability) over SSE?

It does. You configure the MCPToolset with your endpoint, and it handles the SSE or HTTP transport for you. You just define the toolset and pass it to your agent.

Get type-safe observability for Pydantic AI agents using this Datadog 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 Datadog AI (LLM Observability) MCP to Pydantic AI

Create your Vinkius account to connect Datadog AI (LLM 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 Datadog AI (LLM Observability) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate spans with Pydantic AI

Use `search_llm_spans` to ensure your JSON payloads adhere to strict schema definitions. If the response doesn't match your Pydantic model, the agent fails immediately. This prevents silent corruption in your agent's data pipeline. It forces the system to handle errors before they ripple into your business logic.

Enumerate dashboards for Pydantic AI

Call `list_dashboards` to get a structured view of your current billing and active rules. You can then ingest these into your agent's context to inform its decision-making. It turns your monitoring data into actionable input. Your agent knows exactly what limits it faces at any given moment.

Identify accounts for Pydantic AI

Use `list_service_accounts` to map your active arrays against your internal hold parsing logic. It brings transparency to how your services connect to the platform. You gain a clear picture of your service structure without manual audits. It keeps your agent's configuration grounded in the current platform state.

Setup guide

Set up Datadog AI (LLM 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": {
        "datadog-ai-llm-observability-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Datadog AI (LLM 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 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 AI (LLM 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 Datadog AI (LLM Observability) MCP in Pydantic AI

The MCP tool responses are validated against your Pydantic models at runtime. If the server returns unexpected data, the framework catches it instantly.

Yes, by validating spans against your expected output schemas. If the model generates fields that don't fit your model, the agent will throw a validation error.

It does. You configure the `MCPToolset` with your endpoint, and it handles the SSE or HTTP transport for you. You just define the toolset and pass it to your agent.

The server is managed by Vinkius, meaning you don't need to host the infrastructure. You just point your agent at the provided endpoint.

Authentication is handled through a single token managed by the platform. The server never stores your credentials, and all data transfers are ephemeral, ensuring your agent's configuration remains private.

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