How to Use the Datadog MCP in Claude Code

Q: Can I pipe Datadog metrics from Claude Code to other CLI tools using this MCP Server?

Yes, Claude Code outputs raw data from querymetrics directly to stdout. You can pipe this JSON payload into jq or custom shell scripts to automate your on-call alerts.

Q: Can Claude Code list active Datadog alerts during a terminal session?

Yes, Claude Code uses the listmonitors tool to filter and display alerts by their operational state. You can view warning or alert states directly in your terminal without opening the web console.

Q: How do I add this MCP Server to my terminal configuration?

Run claude mcp add --transport http datadog -- to register the server. This adds the configuration to your /.claude.json file, granting immediate command-line access to all eleven tools.

Let Claude Code search logs, query metrics, and manage monitors directly from your terminal.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Datadog MCP to Claude Code

Create your Vinkius account to connect Datadog 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 with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Datadog log searches directly from your terminal

The `search_logs` tool queries your log storage boundary using your custom query syntax directly from the command line. Claude Code executes these searches, pipes the raw JSON output to your terminal, and filters the results using local shell utilities. You can chain this tool with local grep commands to isolate errors during SSH sessions. This saves you from opening a browser during high-severity production outages.

Track scheduled downtimes in your deployment scripts

The `list_downtimes` tool pulls active maintenance windows and recurring schedules into your terminal environment. Claude Code reads these schedules before running automated deployment scripts to confirm you are not pushing updates during a critical window. If an active downtime is detected, Claude Code can pause the execution or alert the on-call engineer. This keeps your CI/CD pipelines aware of manual schedule overrides.

Inspect live metrics via this command-line MCP Server

The `query_metrics` tool retrieves UNIX timestamped time-series data directly into your shell. Claude Code uses this to print ASCII metric trends or feed raw data points into other terminal utilities for quick performance checks. You get instant visibility into CPU spikes and memory leaks without leaving your SSH session. This allows for rapid diagnostics when you are working on headless servers.

Setup guide

Set up Datadog 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-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http datadog-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 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-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 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 MCP in Claude Code

Yes, Claude Code outputs raw data from `query_metrics` directly to stdout. You can pipe this JSON payload into jq or custom shell scripts to automate your on-call alerts.

You pass your API keys as environment variables when running the command-line interface. This headless configuration ensures your credentials are safely injected during GitHub Actions or GitLab runner execution.

Yes, Claude Code uses the `list_monitors` tool to filter and display alerts by their operational state. You can view warning or alert states directly in your terminal without opening the web console.

Run `claude mcp add --transport http datadog -- ` to register the server. This adds the configuration to your `~/.claude.json` file, granting immediate command-line access to all eleven tools.

No, your metric queries and time-series data are processed through an encrypted, memory-only session. Vinkius does not log the payloads of `query_metrics`, keeping your raw telemetry completely private.

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