Datadog MCP Server

Datadog is a monitoring and observability platform for cloud-scale applications, providing infrastructure monitoring, APM, log management, and security monitoring.

Tools

Last Updated

Apr 7, 2026

What is the Datadog MCP Server?

The Datadog MCP server gives AI agents structured, permission-aware access to Datadog through the Model Context Protocol. With 30 pre-built actions, agents can read, create, and update Datadog data on behalf of authorized users.

Willow ships the Datadog MCP server as part of an enterprise control plane. Every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to a full audit trail, and integrates with Splunk and Loki for SIEM visibility. Connect from Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, or any custom agent. Install once, distribute org-wide, and see exactly how Datadog is being used by every AI agent in your stack.

Tools

List Monitors

List all monitors in your Datadog account with optional filtering. Returns monitor configurations including name, type, query, status, and tags. Use this to discover existing monitors or find monitors matching specific criteria. Supports filtering by tags, monitor type, and name.

Search Monitors

Search monitors using Datadog's query syntax. Allows complex queries across monitor attributes including name, status, tags, and configuration. Returns matching monitors with their full configurations. Use this for advanced filtering when simple list filtering isn't sufficient. Example query: 'status:Alert type:metric'

Get Monitor

Retrieve detailed information about a specific monitor by ID. Returns the complete monitor configuration including query, thresholds, notification settings, tags, and current state. Use this when you have a monitor ID and need its full details.

Get Monitor Downtime Schedule

Check if a monitor is currently muted or scheduled for downtime. Returns information about active and scheduled downtimes affecting the specified monitor. Useful for understanding why a monitor might not be alerting.

Validate Monitor

Validate a monitor configuration without creating it. Tests if the monitor query is syntactically correct and will execute properly. Returns validation results indicating whether the configuration is valid. Use this to test monitor configurations before creation.

List Dashboards

List all dashboards in your Datadog account. Returns dashboard summaries including ID, title, description, author, creation date, and URL. Use this to discover available dashboards or get dashboard IDs for detailed retrieval. Supports filtering by tags.

Get Dashboard

Retrieve a complete dashboard configuration by ID. Returns the full dashboard definition including all widgets, layout, template variables, and settings. Use this to inspect dashboard structure, export configurations, or understand widget queries.

Search Dashboards

Search dashboards using a query string. Searches across dashboard titles and returns matching results. Use this to find dashboards by name or keywords when you don't know the exact dashboard ID.

Query Metrics

Query time series metrics data from Datadog. Executes metric queries and returns data points for visualization or analysis. Supports aggregations, filters, and functions. Use this to retrieve metric values over time ranges. Example query: 'avg:system.cpu.idle{*}'

List Active Metrics

List all actively reporting metrics in your Datadog account. Returns metric names that have reported data within a specified time window. Use this to discover available metrics for querying or to verify that expected metrics are reporting. Supports filtering by host and tag.

1 2 3

1–10 of 30 tools

Customize Tools

Edit descriptions, modify arguments, select tools, or add new ones

Set Up Your Datadog MCP Server in Minutes

Add the following configuration to your MCP client. Authentication is handled via OAuth. Compatible with Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, and any MCP-compatible agent.

Claude Desktop

claude_desktop_config.json

{
  "mcpServers": {
    "willow-datadog": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/datadog"
    }
  }
}

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "willow-datadog": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/datadog"
    }
  }
}

Claude Code

CLI

claude mcp add willow-datadog --transport http https://<org>.mcp-s.com/mcp/mcp/datadog

n8n

HTTP Request Node

{
  "url": "https://<org>.mcp-s.com/mcp/mcp/datadog",
  "method": "POST"
}

Or click "Install with Willow" above to set up automatically with SSO and RBAC preconfigured.

Enterprise Governance for Datadog

Willow adds the layer Datadog and every other SaaS doesn't ship out of the box: every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to full audit logs, and detects shadow AI usage across your stack. One MCP gateway. Any agent. Every tool.

Datadog MCP Server FAQ

What is the Datadog MCP server?

The Datadog MCP server is a Model Context Protocol implementation that lets AI agents like Claude, Cursor, and ChatGPT read and write Datadog data through a standardized interface. Willow hosts and governs this server so enterprises can roll it out without a security review backlog.

How is Willow's Datadog MCP server different from the official one?

The official Datadog MCP server is scoped to a single user's account and does not include enterprise governance. Willow's version adds SSO, RBAC, audit logging, shadow AI detection, and centralized control over which actions agents can take across the entire org.

Which AI clients work with the Datadog MCP server?

Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code with MCP support, n8n, and any custom agent built with OpenAI Agents SDK, LangChain, Vercel AI SDK, or Anthropic SDK.

Is the Datadog MCP server secure? How does Willow handle authentication?

Every call runs behind your existing SSO (Okta, Azure AD). Per-user OAuth scopes the agent to exactly what that user can do in Datadog, nothing more. No credentials reach the LLM. Every action writes to an audit trail.

Can I limit which Datadog actions agents can take?

Yes. Willow lets you scope agents to specific actions, specific projects, or specific environments. Toggle actions on or off in the dashboard, or enforce policy via infrastructure-as-code through GitHub.

How do I detect shadow Datadog MCP servers in my org?

Willow's browser extension and discovery service surface unmanaged MCP servers, skills, and AI agents across the org. If a developer installed an unapproved Datadog MCP locally, you'll see it.

What does the Datadog MCP server cost?

Pricing depends on org size and deployment model (SaaS, dedicated cloud, self-host). See withwillow.ai/pricing or contact sales for a quote.

How do I install the Datadog MCP server with Willow?

Install via the Willow Connect Panel in one click, or paste the JSON snippet above into your Claude Desktop, Cursor, or Claude Code config. SSO and RBAC inherit from your existing Willow setup.