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

Q: How do I add Datadog AI (LLM Observability) to Claude Code?

Run claude mcp add --transport http vinkius-datadog -- . Make sure all flags come before the server name. Verify the connection by running claude mcp list.

Q: Can Claude Code submit custom metric series to Datadog?

Yes. Your terminal agent can execute submitseries to perform structural extraction of properties driving active account logic. It pushes these custom LLM metrics directly from your shell environment.

Monitor LLM pipelines from your terminal using Claude Code and 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 Claude Code

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless LLM telemetry for CI/CD pipelines

Terminal workflows demand fast, scriptable access to model performance. You pipe commands to your CLI agent, and it triggers `query_metrics` to pull `datadog.llm_observability.tokens` stats right into your shell session. This setup shines in automated testing. A GitHub Action runs your script, the agent checks `list_incidents` for routing gateway failures, and fails the build if your recent commit spiked token consumption beyond acceptable limits.

Query the Datadog AI (LLM Observability) MCP Server via CLI

SREs need raw data fast during an outage. You ask your agent to investigate a sudden drop in generation quality, and it executes `search_llm_spans` to dump the highly-available JSON payloads into your terminal. You then instruct it to parse the native hold arrays using `list_service_accounts`. The agent cross-references the span data against active service limits, pinpointing exactly which microservice exhausted its quota.

Script automated monitor creation and event logging

Infrastructure as code requires programmatic alert management. Your agent handles this by running `create_monitor` to push explicit validations and rich churn flags directly from your terminal prompt. When a deployment finishes, it automatically fires `create_event` to log the deep internal array changes. You get a complete audit trail of your LLM operations without ever opening a browser window.

Setup guide

Set up Datadog AI (LLM Observability) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see datadog-ai-llm-observability-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Datadog AI (LLM Observability) transactions." It will automatically discover and invoke the available Datadog AI (LLM Observability) tools.

Terminal

claude mcp add --transport http datadog-ai-llm-observability-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "datadog-ai-llm-observability-mcp": {
      "type": "url",
      "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 Code

Run `claude mcp add --transport http vinkius-datadog -- `. Make sure all flags come before the server name. Verify the connection by running `claude mcp list`.

Yes. Your terminal agent can execute `submit_series` to perform structural extraction of properties driving active account logic. It pushes these custom LLM metrics directly from your shell environment.

Vinkius provides HTTP and SSE transports for this integration. The CLI handles the routing automatically, storing the configuration securely in your `~/.claude.json` file.

Just tell your CLI agent to grab your current views. It triggers `list_dashboards` to enumerate explicitly attached structured rules and exports the active billing layouts as text.

We rely on a strict zero-trust architecture for this MCP server. Your CLI agent passes a single endpoint token to Vinkius, which handles the actual Datadog authentication. The terminal only processes the specific incident logs and span arrays you explicitly request.

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