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

Q: How do AutoGen agents share Datadog AI (LLM Observability) data?

One agent calls listdashboards and posts the raw JSON to the group chat. The other agents analyze this data to decide on the next system action.

Q: Can AutoGen agents resolve alerts automatically?

Your agents can use listaimonitors to find active alerts, then execute diagnostic tasks. Once the issue is resolved, they can log the fix using createevent.

Q: How is my prompt data protected when AutoGen queries Datadog?

All prompt logs retrieved via searchllmspans remain strictly within your local AutoGen runtime container. The MCP Server uses ephemeral, zero-trust token isolation to prevent data leaks.

Let your AutoGen agents debate and resolve LLM performance issues using live Datadog metrics.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent triage with MCP Server tools

Your AutoGen agents can collaborate using this MCP Server. A triage agent calls `list_incidents` to find active issues, while a developer agent analyzes the raw traces to find the root cause. They pass this data back and forth to reach a consensus. You get an automated post-mortem without lifting a finger.

Debate and adjust LLM token limits

When token usage spikes, your budget agent calls `query_metrics` to get the latest `datadog.llm_observability.tokens` data. It then argues with the performance agent about whether to throttle requests. Once they agree, they can use `create_event` to log the decision in Datadog. This keeps your team informed of automated changes.

Audit agent conversations using live span data

Your quality assurance agent can call `search_llm_spans` to inspect the actual prompts and responses of other agents in the swarm. It reviews the trace data to ensure no agent is hallucinating. If it detects an anomaly, it alerts the swarm. The agents then adjust their prompts dynamically to correct the behavior.

Setup guide

Set up Datadog AI (LLM Observability) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Datadog AI (LLM Observability) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Datadog AI (LLM Observability)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Datadog AI (LLM Observability) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Datadog AI (LLM Observability)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Datadog AI (LLM Observability) data")
    print(result.messages[-1].content)

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 AutoGen

One agent calls `list_dashboards` and posts the raw JSON to the group chat. The other agents analyze this data to decide on the next system action.

Yes, you can restrict tool access in the agent configuration. For example, you can let your budget agent run `query_metrics` while blocking it from calling `create_monitor`.

Yes, you use the AutoGen MCP tool adapter to convert the server schema. This lets your agents call `list_events` natively without custom parsing code.

Your agents can use `list_ai_monitors` to find active alerts, then execute diagnostic tasks. Once the issue is resolved, they can log the fix using `create_event`.

All prompt logs retrieved via `search_llm_spans` remain strictly within your local AutoGen runtime container. The MCP Server uses ephemeral, zero-trust token isolation to prevent data leaks.

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