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

Inject live Datadog LLM metrics and span data directly into your code with Cursor's AI agent.

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 Cursor

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Write Code with Real-Time Metrics

Stop guessing at metric names. When you're writing a script to analyze LLM costs, just ask the agent, "Get the metric for token usage." It will use the `query_metrics` tool to find `datadog.llm_observability.tokens` and write the actual, working code to query it. This approach grounds the code your agent generates in reality. You don't have to look up schemas or copy-paste from a dashboard. This MCP Server gives the agent live context so it builds correct code on the first try.

Debug LLM Behavior in Your Editor

Trying to figure out why a model is misbehaving? Tell the agent to `search_llm_spans` for a specific trace ID. It will pull the full span details from Datadog and drop them right into your editor as a comment or scratch file. This keeps you in your coding environment. You can see the exact prompts and completions that were sent, check for errors with `list_events`, and inspect related incidents without ever leaving Cursor. It's a tight, efficient feedback loop.

Automate Datadog Setup with your MCP Server

Use the agent to manage your monitoring setup as code. Tell it, "Draft a script to create a new monitor for high latency." The agent can use the `create_monitor` tool to show you the API call structure, which you can then build into your own infrastructure-as-code scripts. It’s about more than just one-off queries. You can use Cursor and this MCP server to build reliable automation around your AI observability, using the agent to scaffold the initial code and verify it works.

Setup guide

Set up Datadog AI (LLM Observability) MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Datadog AI (LLM Observability) MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Datadog AI (LLM Observability) transactions." If the MCP tools are loaded correctly, Cursor will call the Datadog AI (LLM Observability) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

It connects Cursor's agent to your live Datadog account. When you ask the agent to write code that uses LLM metrics, it fetches real metric names and span attributes, so the code it generates actually works.

Yes. Tell the agent, "Find the LLM span with trace ID xyz." It will use the `search_llm_spans` tool to get the data from Datadog and insert it right into your active editor file.

You stay in your editor. Instead of switching contexts to find a metric name or check an incident, you just ask the agent. It keeps you in the flow of coding, which is the whole point of using Cursor.

Yes. You can configure this MCP server globally for all your projects or on a per-project basis by adding it to the `.cursor/mcp.json` file in your repository.

The server only accesses your Datadog AI observability data—things like metric names, span contents, and incident lists. Each request runs in a dedicated, single-use container on Vinkius. Your Datadog credentials are encrypted and managed by the platform, never exposed.

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