Disclaimers

• The Datadog MCP Server is not supported for production use during the Preview.
• Only Datadog organizations that have been specifically allowlisted can use the Datadog MCP Server. It is not available to the general public.
• The Datadog MCP Server is not available for organizations that require HIPAA compliance.
• Datadog collects certain information about your usage of the Remote Datadog MCP Server, including how you interact with it, whether errors occurred while using it, what caused those errors, and user identifiers in accordance with the Datadog Privacy Policy and Datadog’s EULA. This data is used to help improve the server’s performance and features, including transitions to and from the server and the applicable Datadog login page for accessing the Services, and context (for example, user prompts) leading to the use of MCP tools. The data is stored for 120 days.

Overview

Datadog’s managed MCP Server acts as a bridge between your observability data in Datadog and AI agents that support the Model Context Protocol (MCP). Providing structured access to relevant Datadog contexts, features, and tools, the MCP Server lets you query and retrieve observability insights directly from AI-powered clients such as Cursor, OpenAI Codex, Claude Code, or your own AI agent.

This page provides instructions for connecting your AI agent to the Datadog MCP Server, lists the available tools, and includes example prompts.

This demo shows the Datadog MCP Server being used in Cursor and Claude Code (unmute for audio):

Client compatibility

The following AI clients are compatible with the Datadog MCP Server.

Requirements

Datadog users must have the Incidents Read permission to use the MCP Server.

Connect in Cursor and VS Code

Datadog’s Cursor and VS Code extension includes built-in access to the managed Datadog MCP Server. Benefits include:

• No additional MCP Server setup after you install the extension and connect to Datadog.
• One-click transitions between multiple Datadog organizations.
• [Cursor only] Better fixes from Fix in Chat on Code Insights (issues from Error Tracking, Code Vulnerabilities, and Library Vulnerabilities), informed by context from the MCP Server.

To install the extension:

1. If you previously installed the Datadog MCP Server manually, remove it from the IDE’s configuration to avoid conflicts. To find the MCP Server configuration:
   • Cursor: Go to Cursor Settings (Shift + Cmd/Ctrl + J) and select the MCP tab.
   • VS Code: Open the command palette (Shift + Cmd/Ctrl + P) and run MCP: Open User Configuration.
2. Install the Datadog extension following these instructions. If you have the extension installed already, make sure it’s the latest version, as new features are released regularly.
3. Sign in to your Datadog account. If you have multiple accounts, use the account included in your Product Preview.

4. Restart the IDE.
5. Confirm the Datadog MCP Server is available and the tools are listed in your IDE:
   • Cursor: Go to Cursor Settings (Shift + Cmd/Ctrl + J), and select the MCP tab.
   • VS Code: Open the chat panel, select agent mode, and click the Configure Tools button.

Connect in supported AI clients

The following instructions are for all MCP-compatible clients. For Cursor or VS Code, use the Datadog extension for built-in access to the Datadog MCP Server.

Authentication

The MCP Server uses OAuth 2.0 for authentication. If you cannot go through the OAuth flow (for example, on a server), you can provide a Datadog API key and application key as DD_API_KEY and DD_APPLICATION_KEY HTTP headers. For example:

{
  "mcpServers": {
    "datadog": {
      "type": "http",
      "url": "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp",
      "headers": {
          "DD_API_KEY": "<YOUR_API_KEY>",
          "DD_APPLICATION_KEY": "<YOUR_APPLICATION_KEY>"
      }
    }
  }
}

For security, use a scoped API key and application key from a service account that has only the required permissions.

Test access to the MCP Server

1. Install the MCP inspector, a developer tool for testing and debugging MCP servers.

   npx @modelcontextprotocol/inspector
   

2. In the inspector’s web UI, for Transport Type, select Streamable HTTP.

3. For URL, enter the MCP Server URL for your regional Datadog site.

4. Click Connect, then go to Tools > List Tools.

5. Check if the available tools appear.

Toolsets

The Datadog MCP Server supports toolsets, which allow you to use only the tools you need, saving valuable context window space. These toolsets are available:

• core: The default toolset
• synthetics: Tools for interacting with Datadog Synthetic tests
• software-delivery: Tools for interacting with Software Delivery CI Visibility

To use a toolset, include the toolsets query parameter in the endpoint URL when connecting to the MCP Server (remote authentication only). For example:

• https://mcp.datadoghq.com/api/unstable/mcp-server/mcp retrieves only the core tools (this is the default if toolsets is not specified).
• https://mcp.datadoghq.com/api/unstable/mcp-server/mcp?toolsets=synthetics retrieves only Synthetic Testing-related tools.
• https://mcp.datadoghq.com/api/unstable/mcp-server/mcp?toolsets=core,synthetics,software-delivery retrieves core, Synthetic Testing, and Software Delivery tools.

Available tools

This section lists the tools available in the Datadog MCP Server and provides example prompts for using them.

search_datadog_docs

Toolset: core
Returns AI-generated answers to Datadog questions, sourced from Datadog documentation.

• How do you enable Datadog profiling in Python?
• What’s the best way to correlate logs and traces?
• How does RUM auto-instrumentation work?

search_datadog_events

Toolset: core
Searches events like monitor alerts, deployment notifications, infrastructure changes, security findings, and service status changes.

• Show me all deployment events from the last 24 hours.
• Find events related to our production environment with error status.
• Get events tagged with service:api from the past hour.

Note: See the Event Management API for more details.

get_datadog_incident

Toolset: core
Retrieves detailed information about an incident.

• Get details for incident ABC123.
• What’s the status of incident ABC123?
• Retrieve full information about the Redis incident from yesterday.

Note: The tool is operational, but does not include incident timeline data.

get_datadog_metric

Toolset: core
Queries and analyzes historical or real-time metric data, supporting custom queries and aggregations.

• Show me CPU utilization metrics for all hosts in the last 4 hours.
• Get Redis latency metrics for the production environment.
• Display memory usage trends for our database servers.

search_datadog_monitors

Toolset: core
Retrieves information about Datadog monitors, including their statuses, thresholds, and alert conditions.

• List all monitors that are currently alerting.
• Show me monitors related to our payment service.
• Find monitors tagged with team:infrastructure.

get_datadog_trace

Toolset: core
Fetches a complete trace from Datadog APM using a trace ID.

• Get the complete trace for ID 7d5d747be160e280504c099d984bcfe0.
• Show me all spans for trace abc123 with timing information.
• Retrieve trace details including database queries for ID xyz789.

Note: Large traces with thousands of spans may be truncated (and indicated as such) without a way to retrieve all spans.

search_datadog_dashboards

Toolset: core
Lists available Datadog dashboards and key details.

• Show me all available dashboards in our account.
• List dashboards related to infrastructure monitoring.
• Find shared dashboards for the engineering team.

Note: This tool lists relevant dashboards but provides limited detail about their contents.

search_datadog_hosts

Toolset: core
Lists and provides information about monitored hosts, supporting filtering and searching.

• Show me all hosts in our production environment.
• List unhealthy hosts that haven’t reported in the last hour.
• Get all hosts tagged with role:database.

search_datadog_incidents

Toolset: core
Retrieves a list of Datadog incidents, including their state, severity, and metadata.

• Show me all active incidents by severity.
• List resolved incidents from the past week.
• Find incidents that are customer-impacting.

search_datadog_metrics

Toolset: core
Lists available metrics, with options for filtering and metadata.

• Show me all available Redis metrics.
• List CPU-related metrics for our infrastructure.
• Find metrics tagged with service:api.

search_datadog_services

Toolset: core
Lists services in Datadog’s Software Catalog with details and team information.

• Show me all services in our microservices architecture.
• List services owned by the platform team.
• Find services related to payment processing.

search_datadog_spans

Toolset: core
Retrieves spans from APM traces with filters such as service, time, resource, and so on.

• Show me spans with errors from the checkout service.
• Find slow database queries in the last 30 minutes.
• Get spans for failed API requests to our payment service.

search_datadog_logs

Toolset: core
Searches logs with filters (time, query, service, host, storage tier, and so on) and returns log details. Renamed from get_logs.

• Show me error logs from the nginx service in the last hour.
• Find logs containing ‘connection timeout’ from our API service.
• Get all 500 status code logs from production.

search_datadog_rum_events

Toolset: core
Search Datadog RUM events using advanced query syntax.

• Show JavaScript errors and console warnings in RUM.
• Find pages that are loading slowly (more than 3 seconds).
• Show recent user interactions on product detail pages.

get_synthetics_tests

Toolset: synthetics
Searches Datadog Synthetic tests.

• Help me understand why the Synthetic test on endpoint /v1/my/tested/endpoint is failing.
• There is an outage; find all the failing Synthetic tests on the domain api.mycompany.com.
• Are Synthetic tests on my website api.mycompany.com still working in the past hour?

edit_synthetics_tests

Toolset: synthetics
Edits Datadog Synthetic HTTP API tests.

• Improve the assertions of the Synthetic test defined on my endpoint /v1/my/tested/endpoint.
• Pause the test aaa-bbb-ccc and set the locations to only European locations.
• Add my team tag to the test aaa-bbb-ccc.

synthetics_test_wizard

Toolset: synthetics
Preview and create Datadog Synthetics HTTP API Tests.

• Create Synthetics tests on every endpoint defined in this code file.
• Create a Synthetics test on /path/to/endpoint.
• Create a Synthetics test that checks if my domain mycompany.com stays up.

search_datadog_ci_pipeline_events

Toolset: software-delivery
Searches CI events with filters and returns details on them.

• Show me all the pipelines for my commit 58b1488.
• Show me the latest pipeline failure in branch my-branch.
• Propose a fix for the job integration-test that fails every time on my branch my-branch.

Context efficiency

The Datadog MCP Server is optimized to provide responses in a way that AI agents get relevant context without being overloaded with unnecessary information. For example:

• Responses are truncated based on the estimated length of responses each tool provides. The tools respond to AI agents with instructions on how to request more information if the response was truncated.
• Most tools have a max_tokens parameter that enables AI agents to request less or more information.

Track tool calls in Audit Trail

You can view information about calls made by MCP Server tools in Datadog’s Audit Trail. Search or filter by the event name MCP Server.

Feedback

The Datadog MCP Server is under significant development. During the Preview, use this feedback form to share any feedback, use cases, or issues encountered with your prompts and queries.

Further reading

Additional helpful documentation, links, and articles:

Connect your AI agents to Datadog tools and context using the Datadog MCP ServerBLOG Datadog MCP ServerDOCUMENTATION Datadog Extension for CursorDOCUMENTATION Debug live production issues with the Datadog Cursor extensionBLOG Datadog + OpenAI: Codex CLI integration for AI‑assisted DevOpsBLOG