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

Q: Can I track token costs for my models with Datadog AI (LLM Observability) and Claude Desktop?

Yes. You can ask Claude things like, "Query the datadog.llmobservability.tokens metric for the last 24 hours." The server fetches the data from your Datadog account so you can see usage patterns instantly.

Q: Is this just for viewing data?

No, you can also create things. The createmonitor tool, for instance, lets you set up new Datadog monitors simply by asking Claude to do it.

Ask Claude to pull live LLM performance metrics from Datadog right into your chat. No more switching tabs.

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 Claude Desktop

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor LLM Costs and Usage

Get a handle on your model costs. Ask Claude directly about token consumption for any model you're tracking in Datadog. The server uses `query_metrics` to fetch real-time data from `datadog.llm_observability.tokens` and `submit_series` to track custom metrics. This all happens right in your conversation. You're already talking to Claude, so you just ask, "How many tokens did the 'summary-generator' use this week?" You get a number back, not a link to another dashboard. It keeps your focus where it needs to be.

Investigate Incidents from Chat

An alert fires. Instead of digging through Datadog, just ask Claude to pull the details. You can have it `list_incidents` to see what's open, then use `search_llm_spans` to find the exact interaction that caused the problem. This MCP Server connects your conversation directly to your observability data. You get the raw details—span attributes, event logs via `list_events`—right in the chat window. It's the fastest way to start debugging an issue with your AI models.

Manage Datadog Monitors with Claude

This isn't just for reading data. You can make changes to your Datadog setup without leaving the chat. Tell Claude, "Create a new monitor for high token usage on the 'customer-support-bot' model," and the `create_monitor` tool gets it done. You can also check your existing setup with `list_ai_monitors`. It effectively turns your Claude client into a command center for your entire AI observability stack. No need to open the Datadog UI for routine tasks.

Setup guide

Set up Datadog AI (LLM Observability) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Datadog AI (LLM Observability) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Datadog AI (LLM Observability) MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under datadog-ai-llm-observability-mcp.

json

{
  "mcpServers": {
    "datadog-ai-llm-observability-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Desktop

It connects Claude to your Datadog account's API. You ask a question in plain English, this MCP server translates it into a specific API request, and the answer comes right back to you in the chat.

Yes. You can ask Claude things like, "Query the `datadog.llm_observability.tokens` metric for the last 24 hours." The server fetches the data from your Datadog account so you can see usage patterns instantly.

For the desktop app, you add the server to a local config file. On claude.ai, you just paste the Vinkius MCP Server URL into the Custom Connectors settings. The web version is faster for a quick start, while the desktop app can be configured for more complex local workflows.

No, you can also create things. The `create_monitor` tool, for instance, lets you set up new Datadog monitors simply by asking Claude to do it.

This server only handles your Datadog LLM observability data, like span attributes, metric values, and monitor configurations. Vinkius processes requests in an ephemeral, zero-trust sandbox. Your Datadog API keys are managed by the Vinkius platform and are never exposed to your client.

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