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

Q: How does LangChain pass token data to Datadog AI (LLM Observability)?

Your LangChain chain uses submitseries to send custom metrics directly to your dashboard. The agent reads the token count from the previous chain link and posts it immediately.

Q: Can a LangChain agent query active alerts using the Datadog AI (LLM Observability) MCP Server?

Yes, your agent calls listaimonitors to pull active alerts. It uses this live status to decide if it should pause the chain or switch to a backup LLM provider.

Track token usage and monitor LLM performance across your LangChain chains with real-time Datadog observability.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace LangChain tool execution in Datadog

Your LangChain agent can now inspect performance metrics directly inside your runs by calling `query_metrics`. By executing this tool, the agent grabs token counts like `datadog.llm_observability.tokens` to adjust its next chain link dynamically. This means your chain doesn't run blind. If a step spikes in latency, the agent catches it and routes the next call to a cheaper model.

Automate incident response during chain runs

When a step in your LangChain pipeline fails, your agent uses `list_incidents` to check if a wider system outage is causing the issue. It stops guessing whether the LLM or the infrastructure is broken. The agent then calls `create_event` to flag the failure directly in your team's Datadog dashboard. You get immediate visibility without manually parsing raw terminal logs.

Audit live prompts and span data

This MCP Server lets your chain call `search_llm_spans` to pull actual prompt payloads and response times directly from your active Datadog environment. You can audit everything in real time. Your chain gets the exact context it needs to evaluate its own performance. It can inspect raw trace arrays on the fly to flag bad outputs before they reach your users.

Setup guide

Set up Datadog AI (LLM Observability) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Datadog AI (LLM Observability) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "datadog-ai-llm-observability-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Datadog AI (LLM Observability) transactions"
    })
    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 LangChain

Your LangChain chain uses `submit_series` to send custom metrics directly to your dashboard. The agent reads the token count from the previous chain link and posts it immediately.

Yes, your agent calls `list_ai_monitors` to pull active alerts. It uses this live status to decide if it should pause the chain or switch to a backup LLM provider.

You install the LangChain MCP adapter package and pass the server URL to your client. The agent automatically discovers tools like `list_dashboards` to render performance metrics.

While the agent cannot build new layouts from scratch, it uses `list_dashboards` to find existing ones. It then shares the correct dashboard link when reporting issues.

Your local LangChain MCP setup keeps your raw prompt payloads and token metrics secure. All requests go directly between your local runtime and the Datadog API endpoint over HTTPS.

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