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

Q: Can Windsurf Cascade trigger Datadog incidents automatically?

Yes. Your agent can execute createevent to log deep internal array changes or flag specific plan math issues. Cascade decides when an anomaly warrants a formal event based on your instructions.

Q: How do I view my existing LLM monitors through this integration?

Just ask Cascade to check your alert coverage. It calls listaimonitors to pull cloud logging rules and vault limits directly into your chat window.

Track token usage and audit AI prompts directly inside Windsurf using this 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 Windsurf

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomously track token metrics with Windsurf Cascade

Cascade reads your codebase context and automatically pulls relevant LLM telemetry using `query_metrics`. You set a goal to analyze recent API costs, and the agent figures out exactly which token usage numbers to pull from your Datadog environment. Instead of switching tabs to check dashboards, Windsurf chains these checks into your active debugging session. It runs `list_dashboards` to find the right views and immediately cross-references those numbers against your local code changes.

Audit LLM prompts and spans without leaving the editor

Debugging weird model responses requires exact trace data. Your agent executes `search_llm_spans` to fetch the exact JSON payloads and prompt bindings that triggered the failure. Cascade then maps those failing spans back to the specific functions in your project. It uses `list_events` to check if a recent deployment caused the anomaly. You get the actual failure context mapped directly to your local files.

Configure Datadog AI (LLM Observability) MCP Server alerts

Setting up monitors usually involves clicking through web forms. Now you just ask your IDE to handle it. Windsurf triggers `create_monitor` to build validation checks based on your current project thresholds. If something breaks, the agent immediately pulls active flags via `list_incidents`. It ties those alerts directly to the code you just wrote, letting you fix threshold violations before committing.

Setup guide

Set up Datadog AI (LLM Observability) MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Datadog AI (LLM Observability) MCP

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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Datadog AI (LLM Observability) payment history." If connected, Cascade will call the Datadog AI (LLM Observability) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Open your MCP panel and click the Marketplace tab for a one-click install. You can also manually add the server details to your `~/.codeium/windsurf/mcp_config.json` file. Hit refresh and Cascade will auto-discover the new tools.

Yes. Your agent can execute `create_event` to log deep internal array changes or flag specific plan math issues. Cascade decides when an anomaly warrants a formal event based on your instructions.

Cascade chains multi-step actions autonomously. You tell it to investigate a spike in token costs, and it will query metrics, search spans, and read incidents without asking for permission at every step.

Just ask Cascade to check your alert coverage. It calls `list_ai_monitors` to pull cloud logging rules and vault limits directly into your chat window.

Vinkius runs this MCP server inside a V8 Isolate Sandbox. Your agent only accesses the specific token counts and prompt payloads you request via the endpoint token. The connection is ephemeral and leaves no persistent local cache.

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