From cc4ebc6e8852f14f1223281d78a89702abecb582 Mon Sep 17 00:00:00 2001 From: Dominique Alessi Date: Wed, 13 May 2026 12:49:46 -0400 Subject: [PATCH 01/12] Restructure Agentic Onboarding setup page Reorganize the page into three top-level paths (Setup CLI, MCP Server, Skills) and update content per Vidur's draft. Skills section is a placeholder pending the public Skills release. Co-Authored-By: Claude Opus 4.7 (1M context) --- content/en/agentic_onboarding/_index.md | 2 +- content/en/agentic_onboarding/setup.md | 245 ++++++++++++++---------- 2 files changed, 147 insertions(+), 100 deletions(-) diff --git a/content/en/agentic_onboarding/_index.md b/content/en/agentic_onboarding/_index.md index 8b258620dda..47a08ff5c90 100644 --- a/content/en/agentic_onboarding/_index.md +++ b/content/en/agentic_onboarding/_index.md @@ -4,5 +4,5 @@ private: true --- {{< whatsnext desc="Explore Agentic Onboarding" >}} - {{< nextlink href="/agentic_onboarding/setup/" >}}Setup - Set up the Datadog MCP server to instrument your frontend applications with coding agents.{{< /nextlink >}} + {{< nextlink href="/agentic_onboarding/setup/" >}}Setup - Use the AI Setup CLI, the Datadog MCP server, or task-scoped skills to instrument your applications with Datadog.{{< /nextlink >}} {{< /whatsnext >}} diff --git a/content/en/agentic_onboarding/setup.md b/content/en/agentic_onboarding/setup.md index 233f24431a4..c1f4bf22672 100644 --- a/content/en/agentic_onboarding/setup.md +++ b/content/en/agentic_onboarding/setup.md @@ -1,6 +1,6 @@ --- title: Agentic Onboarding Setup -description: Set up the Datadog MCP server to instrument your applications with coding agents like Cursor or Claude Code. +description: Set up Datadog instrumentation with the AI Setup CLI, the Datadog MCP server, or task-scoped skills for Claude. --- @@ -10,145 +10,192 @@ Agentic Onboarding is in Preview. ## Overview -Agentic Onboarding lets LLM coding agents instrument your frontend applications for [Error Tracking][3], [Real User Monitoring (RUM)][4], [Product Analytics][5], [Infrastructure Monitoring][8], and [Serverless Monitoring][7] with a single prompt. +Agentic Onboarding lets LLM coding agents instrument your applications and infrastructure for [Error Tracking][1], [Real User Monitoring (RUM)][2], [Product Analytics][3], [Infrastructure Monitoring][4], and [Serverless Monitoring][5]. -Your coding assistant, such as [Cursor][1] or [Claude Code][2], detects your project's frameworks, adds configuration, and provisions required tokens and apps directly from your IDE. +There are three ways to get started. Pick the one that matches how you work: -## Supported frameworks -Agentic Onboarding is available for the following frameworks: -- **Error Tracking, RUM, and Product Analytics**: Android, Angular, iOS, Next.js, React, Svelte, Vanilla JS, and Vue. -- **Infrastructure Monitoring with Kubernetes**: Terraform, Ansible, Kustomize, and more. -- **Serverless Monitoring for AWS Lambda**: Terraform, AWS CDK, Serverless Framework, and more. +| Path | Use when | +|------|----------| +| [Setup CLI](#setup-cli) | You want a standalone command-line tool, no coding assistant required. Useful for first-time account creation, linking an existing account, or instrumenting local IaC and application code from a terminal. | +| [MCP server](#mcp-server) | You work with an LLM coding assistant (Claude Code, Cursor, and so on) and want it to detect frameworks, write configuration, and provision tokens directly from your IDE. | +| [Skills](#skills) | You're using Claude and want task-scoped skills for specific onboarding steps (install the Agent, enable a cloud integration, and so on) rather than a full MCP toolset. | -## Setup +The three paths are complementary. You can install the MCP server in your IDE, run the CLI in a terminal, and invoke skills from Claude—all against the same Datadog account. -### Install the Datadog Onboarding MCP server +## Setup CLI -To install the Datadog Onboarding Model Context Protocol (MCP) server, follow the steps for your coding assistant: +The Datadog AI Setup CLI is a standalone tool that runs from your terminal. Use it when you don't want to install an MCP server, or when you need to do something the MCP flow doesn't cover—typically account bootstrapping. -{{< tabs >}} -{{% tab "Claude Code" %}} -{{< site-region region="gov,gov2" >}} -
Agentic Onboarding is not available in the selected site ({{< region-param key="dd_site_name" >}}).
-{{< /site-region >}} +The CLI can: + +- Create a Datadog account end-to-end from the terminal. +- Link an existing Datadog account to your local environment. +- Instrument local infrastructure-as-code (Terraform, Helm, Kustomize, Ansible, Pulumi, raw Kubernetes manifests) by editing files in place. +- Instrument local application code by adding SDK initialization and configuration for supported frontends and backends. + +### Install and run + +Run the CLI with `npx`, replacing `` with one of: `error-tracking`, `rum`, `product-analytics`, `kubernetes`, `docker`, or `serverless`: + +```shell +npx @datadog/ai-setup-cli --product +``` + +To walk through account setup and product selection interactively, run the CLI with no arguments: + +```shell +npx @datadog/ai-setup-cli +``` + +A browser window opens for authentication. After you complete the OAuth flow, return to your terminal. The CLI detects your project's frameworks, applies the required configuration, and provisions any necessary tokens. + +### Example flows + +**First-time user, no Datadog account yet:** + +```shell +npx @datadog/ai-setup-cli +# Prompts for account creation, then product selection. +``` + +**Existing account, instrumenting a local Terraform repo for Kubernetes:** + +```shell +cd my-k8s-terraform-repo +npx @datadog/ai-setup-cli --product kubernetes +# Detects Terraform, adds the Datadog Agent module, and writes the API key to .env. +``` + +After the CLI completes, see [Next steps](#next-steps). + +## MCP Server + +The Datadog MCP server exposes the `onboarding` toolset to any MCP-compatible coding assistant. After you install and authenticate the server, you instrument a project by typing a one-line prompt. The agent reads your code, calls MCP tools (with your permission), applies changes, and verifies the result. + +### Supported frameworks -{{< site-region region="us,us3,us5,eu,ap1,ap2" >}} -1. Open an active Claude Code session with the /mcp command: +| Product | Frameworks | +|---------|------------| +| Error Tracking, RUM, Product Analytics | Android, Angular, iOS, Next.js, React, Svelte, Vanilla JS, Vue | +| Infrastructure Monitoring (Kubernetes) | Terraform, Ansible, Kustomize, Helm, Pulumi, raw manifests | +| Serverless Monitoring (AWS Lambda) | Terraform, AWS CDK, Serverless Framework, SAM | - 
-   claude mcp add --transport http datadog-onboarding-{{< region-param key=dd_datacenter_lowercase >}} "https://mcp.{{< region-param key=dd_site >}}/api/unstable/mcp-server/mcp?toolsets=onboarding"
-
+### Install -2. Select the MCP server installed in Step 1. You should see a `disconnected - Enter to login` message. Press Enter. -3. When you see the option to authenticate, press Enter. This brings you to the OAuth screen. -4. After authentication, choose {{< ui >}}Open{{< /ui >}} to continue and grant access to your Datadog account. -5. Confirm that MCP tools appear under the **datadog-onboarding-{{< region-param key=dd_datacenter_lowercase >}}** server. -{{< /site-region >}} +{{< tabs >}} +{{% tab "Claude Code" %}} +In an active Claude Code session, run: + 
claude mcp add --transport http datadog-onboarding-{{< region-param key="dd_datacenter_lowercase" >}} "{{< region-param key="mcp_server_endpoint" >}}?toolsets=onboarding"
{{% /tab %}} {{% tab "Cursor" %}} -{{< site-region region="gov,gov2" >}} -
Agentic Onboarding is not available in the selected site ({{< region-param key="dd_site_name" >}}).
-{{< /site-region >}} +Click the install deeplink for your [Datadog site][1]: + + 
{{< region-param key="cursor_mcp_install_deeplink" >}}
-{{< site-region region="us,us3,us5,eu,ap1,ap2" >}} -1. Copy and paste the following deeplink into your browser: +Alternatively, add the server manually in `~/.cursor/mcp.json`: - 
-   {{< region-param key=cursor_mcp_install_deeplink >}}
-
+ 
{
+  "mcpServers": {
+    "datadog-onboarding-{{< region-param key="dd_datacenter_lowercase" >}}": {
+      "url": "{{< region-param key="mcp_server_endpoint" >}}?toolsets=onboarding"
+    }
+  }
+}
-2. In Cursor, click {{< ui >}}Install{{< /ui >}} for the **datadog-onboarding-{{< region-param key=dd_datacenter_lowercase >}}** server. -3. If the MCP server shows a {{< ui >}}Needs login{{< /ui >}} or {{< ui >}}Connect{{< /ui >}} link, select it and complete the OAuth flow. When prompted, choose {{< ui >}}Open{{< /ui >}} to continue and grant access to your Datadog account. -4. After authentication, return to Cursor and confirm that MCP tools appear under the **datadog-onboarding-{{< region-param key=dd_datacenter_lowercase >}}** server. -{{< /site-region >}} +In Cursor, click {{< ui >}}Install{{< /ui >}} for the **datadog-onboarding-{{< region-param key="dd_datacenter_lowercase" >}}** server. +[1]: /getting_started/site/ {{% /tab %}} -{{% tab "Datadog AI Setup CLI" %}} -{{< site-region region="gov" >}} -
Agentic Onboarding is not available in the selected site ({{< region-param key="dd_site_name" >}}).
-{{< /site-region >}} +{{% tab "Other MCP clients" %}} +Any MCP client that supports HTTP transport works. Point it at the endpoint for your [Datadog site][1]: -{{< site-region region="us,us3,us5,eu,ap1,ap2" >}} -The Datadog AI Setup CLI configures your project without a coding assistant. + 
{{< region-param key="mcp_server_endpoint" >}}?toolsets=onboarding
-1. Run the `npx` command, replacing `` with the identifier for the product you want to set up: +[1]: /getting_started/site/ +{{% /tab %}} +{{< /tabs >}} - | Product | Identifier | - |---------|------------| - | Error Tracking | `error-tracking` | - | Infrastructure Monitoring | `infra-monitoring` | - | Product Analytics | `product-analytics` | - | Real User Monitoring | `rum` | - | Studio | `studio` | +### Authenticate - ```shell - npx @datadog/ai-setup-cli --product - ``` +1. When prompted to authenticate, press Enter. This opens the Datadog OAuth screen in your browser. +1. After authentication completes, choose {{< ui >}}Open{{< /ui >}} to return to your IDE and grant the MCP server access to your Datadog account. +1. Confirm that MCP tools appear under the **datadog-onboarding-{{< region-param key="dd_datacenter_lowercase" >}}** server. -2. A browser window opens for authentication. Complete the OAuth flow and grant access to your Datadog account. -3. Return to your terminal. The CLI detects your project's frameworks, applies the required configuration, and provisions any necessary tokens. +### Instrument your project -After the CLI completes, skip to [Deploy your app to production](#deploy-your-app-to-production). -{{< /site-region >}} +Send the prompt that matches the product you want to install: +{{< tabs >}} +{{% tab "Error Tracking" %}} +{{< code-block lang="text" >}}Add Datadog Error Tracking to my project{{< /code-block >}} +{{% /tab %}} + +{{% tab "Real User Monitoring" %}} +{{< code-block lang="text" >}}Add Datadog Real User Monitoring to my project{{< /code-block >}} {{% /tab %}} -{{< /tabs >}} -### Set up your project +{{% tab "Product Analytics" %}} +{{< code-block lang="text" >}}Add Datadog Product Analytics to my project{{< /code-block >}} +{{% /tab %}} -Your AI coding agent can help configure Datadog for your project. When you provide a setup prompt, the agent: +{{% tab "Kubernetes" %}} +{{< code-block lang="text" >}}Add Datadog for Kubernetes to my project{{< /code-block >}} +{{% /tab %}} -- Analyzes your project and identifies the framework, language, and bundler -- Calls the MCP tool and requests permission before running -- Applies the configuration changes specified by the tool -- Provides steps to verify that your application is sending telemetry to Datadog +{{% tab "Docker" %}} +{{< code-block lang="text" >}}Add Datadog for Docker to my project{{< /code-block >}} +{{% /tab %}} + +{{% tab "Serverless" %}} +{{< code-block lang="text" >}}Instrument my AWS Lambda functions with Datadog{{< /code-block >}} +{{% /tab %}} +{{< /tabs >}} + +The agent detects your stack, requests permission before each tool call, applies changes, and prints verification steps. **Note**: Your coding agent makes changes locally but does not commit them. -To get started: -1. Choose the product you want to use and paste its setup prompt into your AI agent: +After the agent completes, see [Next steps](#next-steps). + +## Skills + +Skills are task-scoped capabilities for Claude. The MCP server exposes a broad onboarding toolset, but a skill is a focused workflow for a single onboarding step. Use a skill when you only need one thing done and don't want to load a full MCP server. - {{< tabs >}} - {{% tab "Error Tracking" %}} - {{< code-block lang="text" >}}Add Datadog Error Tracking to my project{{< /code-block >}} - {{% /tab %}} +
This section is in progress. Additional onboarding skills are planned, and the content below is subject to change before general availability.
- {{% tab "Real User Monitoring" %}} - {{< code-block lang="text" >}}Add Datadog Real User Monitoring to my project{{< /code-block >}} - {{% /tab %}} +### Available skills - {{% tab "Product Analytics" %}} - {{< code-block lang="text" >}}Add Datadog Product Analytics to my project{{< /code-block >}} - {{% /tab %}} +| Skill | What it does | +|-------|--------------| +| Install Datadog Agent | Detects the host or cluster type and installs the Datadog Agent with the right configuration. | +| Enable cloud integration | Wires up AWS, GCP, or Azure cloud integrations against your Datadog account. | - {{% tab "Infrastructure Monitoring" %}} - **Kubernetes** - {{< code-block lang="text" >}}Add Datadog for Kubernetes to my project{{< /code-block >}} +### How to invoke - **Docker** - {{< code-block lang="text" >}}Add Datadog for Docker to my project{{< /code-block >}} - {{% /tab %}} +Skills are discoverable inside Claude. From a Claude conversation: - {{% tab "Serverless Monitoring" %}} - {{< code-block lang="text" >}}Instrument my AWS Lambda functions with Datadog{{< /code-block >}} - {{% /tab %}} - {{< /tabs >}} +1. Reference the skill by name (for example, "install the Datadog Agent on this host"). +1. Claude loads the skill, asks for any required credentials or scope (host or cluster, cloud account ID, and so on), and walks through the steps. +1. The skill prints verification commands when it finishes. -2. Review and accept each action your AI agent proposes to complete the setup process. +Skills work standalone—you don't need the MCP server installed to use them. -### Deploy your app to production +## Next steps -Commit the changes to your repository and configure the provided environment variables in your production environment. +After any of the three paths completes: -[1]: https://cursor.com/ -[2]: https://claude.ai/ -[3]: /error_tracking/frontend/ -[4]: /real_user_monitoring/ -[5]: /product_analytics/ -[6]: /integrations/kubernetes -[7]: /serverless/ -[8]: /containers/kubernetes/ +- Commit the agent-generated configuration to your repository, and set any new environment variables (API keys, application IDs) in your production environment. For team-wide rollout, propagate these variables through your secret manager. +- Confirm data is flowing in the Datadog UI: [APM > Services][6], [RUM > Applications][7], [Infrastructure > Hosts][8], or [Logs > Live Tail][9]. +[1]: /error_tracking/frontend/ +[2]: /real_user_monitoring/ +[3]: /product_analytics/ +[4]: /containers/kubernetes/ +[5]: /serverless/ +[6]: https://app.datadoghq.com/services +[7]: https://app.datadoghq.com/rum/list +[8]: https://app.datadoghq.com/infrastructure +[9]: https://app.datadoghq.com/logs/livetail From c95c176416ba443aac6cc33c2f7b875dab4c8977 Mon Sep 17 00:00:00 2001 From: Dominique Alessi Date: Wed, 13 May 2026 14:37:24 -0400 Subject: [PATCH 02/12] Apply editorial review Standardize "MCP Server" capitalization, restructure the Cursor install tab as two distinct methods, replace afterthought em dashes with periods or restructured clauses, and rephrase "and so on" trail-offs. Co-Authored-By: Claude Opus 4.7 (1M context) --- content/en/agentic_onboarding/_index.md | 2 +- content/en/agentic_onboarding/setup.md | 36 +++++++++++-------------- 2 files changed, 17 insertions(+), 21 deletions(-) diff --git a/content/en/agentic_onboarding/_index.md b/content/en/agentic_onboarding/_index.md index 47a08ff5c90..f34712591fa 100644 --- a/content/en/agentic_onboarding/_index.md +++ b/content/en/agentic_onboarding/_index.md @@ -4,5 +4,5 @@ private: true --- {{< whatsnext desc="Explore Agentic Onboarding" >}} - {{< nextlink href="/agentic_onboarding/setup/" >}}Setup - Use the AI Setup CLI, the Datadog MCP server, or task-scoped skills to instrument your applications with Datadog.{{< /nextlink >}} + {{< nextlink href="/agentic_onboarding/setup/" >}}Setup - Use the AI Setup CLI, the Datadog MCP Server, or task-scoped skills to instrument your applications with Datadog.{{< /nextlink >}} {{< /whatsnext >}} diff --git a/content/en/agentic_onboarding/setup.md b/content/en/agentic_onboarding/setup.md index c1f4bf22672..f9fb8be4ee2 100644 --- a/content/en/agentic_onboarding/setup.md +++ b/content/en/agentic_onboarding/setup.md @@ -1,6 +1,6 @@ --- title: Agentic Onboarding Setup -description: Set up Datadog instrumentation with the AI Setup CLI, the Datadog MCP server, or task-scoped skills for Claude. +description: Set up Datadog instrumentation with the AI Setup CLI, the Datadog MCP Server, or task-scoped skills for Claude. --- @@ -17,14 +17,14 @@ There are three ways to get started. Pick the one that matches how you work: | Path | Use when | |------|----------| | [Setup CLI](#setup-cli) | You want a standalone command-line tool, no coding assistant required. Useful for first-time account creation, linking an existing account, or instrumenting local IaC and application code from a terminal. | -| [MCP server](#mcp-server) | You work with an LLM coding assistant (Claude Code, Cursor, and so on) and want it to detect frameworks, write configuration, and provision tokens directly from your IDE. | -| [Skills](#skills) | You're using Claude and want task-scoped skills for specific onboarding steps (install the Agent, enable a cloud integration, and so on) rather than a full MCP toolset. | +| [MCP Server](#mcp-server) | You work with an LLM coding assistant (such as Claude Code or Cursor) and want it to detect frameworks, write configuration, and provision tokens directly from your IDE. | +| [Skills](#skills) | You're using Claude and want task-scoped skills for specific onboarding steps (such as installing the Agent or enabling a cloud integration) rather than a full MCP toolset. | -The three paths are complementary. You can install the MCP server in your IDE, run the CLI in a terminal, and invoke skills from Claude—all against the same Datadog account. +The three paths are complementary and work against the same Datadog account. You can install the Datadog MCP Server in your IDE, run the CLI in a terminal, and invoke skills from Claude. ## Setup CLI -The Datadog AI Setup CLI is a standalone tool that runs from your terminal. Use it when you don't want to install an MCP server, or when you need to do something the MCP flow doesn't cover—typically account bootstrapping. +The Datadog AI Setup CLI is a standalone tool that runs from your terminal. Use it when you don't want to install an MCP server, or when you need to do something the MCP flow doesn't cover, such as account bootstrapping. The CLI can: @@ -70,7 +70,7 @@ After the CLI completes, see [Next steps](#next-steps). ## MCP Server -The Datadog MCP server exposes the `onboarding` toolset to any MCP-compatible coding assistant. After you install and authenticate the server, you instrument a project by typing a one-line prompt. The agent reads your code, calls MCP tools (with your permission), applies changes, and verifies the result. +The Datadog MCP Server exposes the `onboarding` toolset to any MCP-compatible coding assistant. After you install and authenticate the server, you instrument a project by typing a one-line prompt. The agent reads your code, calls MCP tools (with your permission), applies changes, and verifies the result. ### Supported frameworks @@ -90,11 +90,13 @@ In an active Claude Code session, run: {{% /tab %}} {{% tab "Cursor" %}} -Click the install deeplink for your [Datadog site][1]: +Install the MCP Server using one of the following methods. + +**Deeplink (recommended)**: Click the install deeplink for your [Datadog site](/getting_started/site/), then click {{< ui >}}Install{{< /ui >}} in Cursor for the **datadog-onboarding-{{< region-param key="dd_datacenter_lowercase" >}}** server: 
{{< region-param key="cursor_mcp_install_deeplink" >}}
-Alternatively, add the server manually in `~/.cursor/mcp.json`: +**Manual configuration**: Add the server to `~/.cursor/mcp.json`: 
{
   "mcpServers": {
@@ -103,25 +105,19 @@ Alternatively, add the server manually in `~/.cursor/mcp.json`:
     }
   }
 }
- -In Cursor, click {{< ui >}}Install{{< /ui >}} for the **datadog-onboarding-{{< region-param key="dd_datacenter_lowercase" >}}** server. - -[1]: /getting_started/site/ {{% /tab %}} {{% tab "Other MCP clients" %}} -Any MCP client that supports HTTP transport works. Point it at the endpoint for your [Datadog site][1]: +Any MCP client that supports HTTP transport works. Point it at the endpoint for your [Datadog site](/getting_started/site/): 
{{< region-param key="mcp_server_endpoint" >}}?toolsets=onboarding
- -[1]: /getting_started/site/ {{% /tab %}} {{< /tabs >}} ### Authenticate 1. When prompted to authenticate, press Enter. This opens the Datadog OAuth screen in your browser. -1. After authentication completes, choose {{< ui >}}Open{{< /ui >}} to return to your IDE and grant the MCP server access to your Datadog account. +1. After authentication completes, choose {{< ui >}}Open{{< /ui >}} to return to your IDE and grant the MCP Server access to your Datadog account. 1. Confirm that MCP tools appear under the **datadog-onboarding-{{< region-param key="dd_datacenter_lowercase" >}}** server. ### Instrument your project @@ -162,7 +158,7 @@ After the agent completes, see [Next steps](#next-steps). ## Skills -Skills are task-scoped capabilities for Claude. The MCP server exposes a broad onboarding toolset, but a skill is a focused workflow for a single onboarding step. Use a skill when you only need one thing done and don't want to load a full MCP server. +Skills are task-scoped capabilities for Claude. The Datadog MCP Server exposes a broad onboarding toolset, but a skill is a focused workflow for a single onboarding step. Use a skill when you only need one thing done and don't want to load a full MCP server.
This section is in progress. Additional onboarding skills are planned, and the content below is subject to change before general availability.
@@ -178,14 +174,14 @@ Skills are task-scoped capabilities for Claude. The MCP server exposes a broad o Skills are discoverable inside Claude. From a Claude conversation: 1. Reference the skill by name (for example, "install the Datadog Agent on this host"). -1. Claude loads the skill, asks for any required credentials or scope (host or cluster, cloud account ID, and so on), and walks through the steps. +1. Claude loads the skill, asks for any required credentials or scope (such as host or cluster type, or cloud account ID), and walks through the steps. 1. The skill prints verification commands when it finishes. -Skills work standalone—you don't need the MCP server installed to use them. +Skills work standalone, so you don't need the MCP Server installed to use them. After the skill completes, see [Next steps](#next-steps). ## Next steps -After any of the three paths completes: +After your setup completes: - Commit the agent-generated configuration to your repository, and set any new environment variables (API keys, application IDs) in your production environment. For team-wide rollout, propagate these variables through your secret manager. - Confirm data is flowing in the Datadog UI: [APM > Services][6], [RUM > Applications][7], [Infrastructure > Hosts][8], or [Logs > Live Tail][9]. From 9097b628f479697495e5b2fb8452fa80642acc90 Mon Sep 17 00:00:00 2001 From: Dominique Alessi Date: Wed, 13 May 2026 14:44:53 -0400 Subject: [PATCH 03/12] Apply structural review pass Expand IaC on first mention, harmonize the Overview table cells as single sentences with a parallel "You..." opener, and replace generic MCP and Skills H3 headings with retrieval-friendly variants. Co-Authored-By: Claude Opus 4.7 (1M context) --- content/en/agentic_onboarding/setup.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/content/en/agentic_onboarding/setup.md b/content/en/agentic_onboarding/setup.md index f9fb8be4ee2..c44ae1c0ad6 100644 --- a/content/en/agentic_onboarding/setup.md +++ b/content/en/agentic_onboarding/setup.md @@ -16,9 +16,9 @@ There are three ways to get started. Pick the one that matches how you work: | Path | Use when | |------|----------| -| [Setup CLI](#setup-cli) | You want a standalone command-line tool, no coding assistant required. Useful for first-time account creation, linking an existing account, or instrumenting local IaC and application code from a terminal. | +| [Setup CLI](#setup-cli) | You want a standalone command-line tool (no coding assistant required) for first-time account creation, linking an existing account, or instrumenting local infrastructure-as-code (IaC) and application code from a terminal. | | [MCP Server](#mcp-server) | You work with an LLM coding assistant (such as Claude Code or Cursor) and want it to detect frameworks, write configuration, and provision tokens directly from your IDE. | -| [Skills](#skills) | You're using Claude and want task-scoped skills for specific onboarding steps (such as installing the Agent or enabling a cloud integration) rather than a full MCP toolset. | +| [Skills](#skills) | You're using Claude and want a focused skill for a single onboarding step (such as installing the Agent or enabling a cloud integration) rather than a full MCP toolset. | The three paths are complementary and work against the same Datadog account. You can install the Datadog MCP Server in your IDE, run the CLI in a terminal, and invoke skills from Claude. @@ -80,7 +80,7 @@ The Datadog MCP Server exposes the `onboarding` toolset to any MCP-compatible co | Infrastructure Monitoring (Kubernetes) | Terraform, Ansible, Kustomize, Helm, Pulumi, raw manifests | | Serverless Monitoring (AWS Lambda) | Terraform, AWS CDK, Serverless Framework, SAM | -### Install +### Install the MCP Server {{< tabs >}} {{% tab "Claude Code" %}} @@ -114,7 +114,7 @@ Any MCP client that supports HTTP transport works. Point it at the endpoint for {{% /tab %}} {{< /tabs >}} -### Authenticate +### Authenticate the MCP Server 1. When prompted to authenticate, press Enter. This opens the Datadog OAuth screen in your browser. 1. After authentication completes, choose {{< ui >}}Open{{< /ui >}} to return to your IDE and grant the MCP Server access to your Datadog account. @@ -169,7 +169,7 @@ Skills are task-scoped capabilities for Claude. The Datadog MCP Server exposes a | Install Datadog Agent | Detects the host or cluster type and installs the Datadog Agent with the right configuration. | | Enable cloud integration | Wires up AWS, GCP, or Azure cloud integrations against your Datadog account. | -### How to invoke +### Invoke a skill Skills are discoverable inside Claude. From a Claude conversation: From eb8691dc1c8089d4e9c65f6e593b0c1389b442fb Mon Sep 17 00:00:00 2001 From: Dominique Alessi Date: Wed, 13 May 2026 15:02:26 -0400 Subject: [PATCH 04/12] Drop end periods from the Setup CLI capabilities list Items are verb-phrase fragments, so they take no end punctuation per the editorial standard. Co-Authored-By: Claude Opus 4.7 (1M context) --- content/en/agentic_onboarding/setup.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/content/en/agentic_onboarding/setup.md b/content/en/agentic_onboarding/setup.md index c44ae1c0ad6..27ffbeb2d57 100644 --- a/content/en/agentic_onboarding/setup.md +++ b/content/en/agentic_onboarding/setup.md @@ -28,10 +28,10 @@ The Datadog AI Setup CLI is a standalone tool that runs from your terminal. Use The CLI can: -- Create a Datadog account end-to-end from the terminal. -- Link an existing Datadog account to your local environment. -- Instrument local infrastructure-as-code (Terraform, Helm, Kustomize, Ansible, Pulumi, raw Kubernetes manifests) by editing files in place. -- Instrument local application code by adding SDK initialization and configuration for supported frontends and backends. +- Create a Datadog account end-to-end from the terminal +- Link an existing Datadog account to your local environment +- Instrument local infrastructure-as-code (Terraform, Helm, Kustomize, Ansible, Pulumi, raw Kubernetes manifests) by editing files in place +- Instrument local application code by adding SDK initialization and configuration for supported frontends and backends ### Install and run From 3fe92b7c121695b97abe6cb228d5712c7cbd0f33 Mon Sep 17 00:00:00 2001 From: Dominique Alessi Date: Wed, 13 May 2026 15:04:12 -0400 Subject: [PATCH 05/12] Invert the Setup CLI install order Lead with the interactive no-flag command and present --product as a shortcut. This matches the progression in the Example flows section below (first-time user before existing-account) and lets readers run a command before learning the product identifiers. Co-Authored-By: Claude Opus 4.7 (1M context) --- content/en/agentic_onboarding/setup.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/content/en/agentic_onboarding/setup.md b/content/en/agentic_onboarding/setup.md index 27ffbeb2d57..1c49745bd72 100644 --- a/content/en/agentic_onboarding/setup.md +++ b/content/en/agentic_onboarding/setup.md @@ -35,20 +35,20 @@ The CLI can: ### Install and run -Run the CLI with `npx`, replacing `` with one of: `error-tracking`, `rum`, `product-analytics`, `kubernetes`, `docker`, or `serverless`: +Run the CLI with `npx`: ```shell -npx @datadog/ai-setup-cli --product +npx @datadog/ai-setup-cli ``` -To walk through account setup and product selection interactively, run the CLI with no arguments: +A browser window opens for authentication. After you complete the OAuth flow, return to your terminal. The CLI walks you through account setup and product selection, detects your project's frameworks, applies the required configuration, and provisions any necessary tokens. + +To skip product selection, pass `--product` with one of `error-tracking`, `rum`, `product-analytics`, `kubernetes`, `docker`, or `serverless`: ```shell -npx @datadog/ai-setup-cli +npx @datadog/ai-setup-cli --product ``` -A browser window opens for authentication. After you complete the OAuth flow, return to your terminal. The CLI detects your project's frameworks, applies the required configuration, and provisions any necessary tokens. - ### Example flows **First-time user, no Datadog account yet:** From 6d4c8ea52996f1db14a8b1b62a0c0bfcb4a064bb Mon Sep 17 00:00:00 2001 From: Dominique Alessi Date: Wed, 13 May 2026 15:10:37 -0400 Subject: [PATCH 06/12] Move deploy step into the Setup CLI and MCP Server sections Both paths produce local file changes that must be committed and deployed, but the Skills path doesn't always. Move the commit + env var instructions out of Next steps and into each applicable section, leaving Next steps as a single universal verification step. Co-Authored-By: Claude Opus 4.7 (1M context) --- content/en/agentic_onboarding/setup.md | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/content/en/agentic_onboarding/setup.md b/content/en/agentic_onboarding/setup.md index 1c49745bd72..3d6e6e5a20d 100644 --- a/content/en/agentic_onboarding/setup.md +++ b/content/en/agentic_onboarding/setup.md @@ -66,7 +66,7 @@ npx @datadog/ai-setup-cli --product kubernetes # Detects Terraform, adds the Datadog Agent module, and writes the API key to .env. ``` -After the CLI completes, see [Next steps](#next-steps). +After the CLI completes, commit the changes to your repository and set any new environment variables (API keys, application IDs) in your production environment. Then see [Next steps](#next-steps) to confirm data is flowing. ## MCP Server @@ -154,7 +154,7 @@ The agent detects your stack, requests permission before each tool call, applies **Note**: Your coding agent makes changes locally but does not commit them. -After the agent completes, see [Next steps](#next-steps). +After the agent completes, commit the changes to your repository and set any new environment variables (API keys, application IDs) in your production environment. Then see [Next steps](#next-steps) to confirm data is flowing. ## Skills @@ -181,10 +181,7 @@ Skills work standalone, so you don't need the MCP Server installed to use them. ## Next steps -After your setup completes: - -- Commit the agent-generated configuration to your repository, and set any new environment variables (API keys, application IDs) in your production environment. For team-wide rollout, propagate these variables through your secret manager. -- Confirm data is flowing in the Datadog UI: [APM > Services][6], [RUM > Applications][7], [Infrastructure > Hosts][8], or [Logs > Live Tail][9]. +Confirm data is flowing in the Datadog UI: [APM > Services][6], [RUM > Applications][7], [Infrastructure > Hosts][8], or [Logs > Live Tail][9]. [1]: /error_tracking/frontend/ [2]: /real_user_monitoring/ From 303809190809489d75e4ddd7d0505e07dbb3edb6 Mon Sep 17 00:00:00 2001 From: Dominique Alessi Date: Wed, 13 May 2026 15:13:56 -0400 Subject: [PATCH 07/12] Tighten Overview table cells Each cell now carries a single decision-driving sentence; examples and mechanics live in the section the row links to. Co-Authored-By: Claude Opus 4.7 (1M context) --- content/en/agentic_onboarding/setup.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/content/en/agentic_onboarding/setup.md b/content/en/agentic_onboarding/setup.md index 3d6e6e5a20d..fa134400f3a 100644 --- a/content/en/agentic_onboarding/setup.md +++ b/content/en/agentic_onboarding/setup.md @@ -16,9 +16,9 @@ There are three ways to get started. Pick the one that matches how you work: | Path | Use when | |------|----------| -| [Setup CLI](#setup-cli) | You want a standalone command-line tool (no coding assistant required) for first-time account creation, linking an existing account, or instrumenting local infrastructure-as-code (IaC) and application code from a terminal. | -| [MCP Server](#mcp-server) | You work with an LLM coding assistant (such as Claude Code or Cursor) and want it to detect frameworks, write configuration, and provision tokens directly from your IDE. | -| [Skills](#skills) | You're using Claude and want a focused skill for a single onboarding step (such as installing the Agent or enabling a cloud integration) rather than a full MCP toolset. | +| [Setup CLI](#setup-cli) | You want to set up Datadog from a terminal, without an AI coding assistant. | +| [MCP Server](#mcp-server) | You use an LLM coding assistant (such as Claude Code or Cursor) and want it to handle framework detection and configuration from your IDE. | +| [Skills](#skills) | You want a focused, single-task workflow in Claude rather than a full MCP toolset. | The three paths are complementary and work against the same Datadog account. You can install the Datadog MCP Server in your IDE, run the CLI in a terminal, and invoke skills from Claude. From 8dd7564169ad153c015d1141719647ae0fad5581 Mon Sep 17 00:00:00 2001 From: Dominique Alessi Date: Wed, 13 May 2026 15:19:01 -0400 Subject: [PATCH 08/12] Restructure CLI install section as a when-to-use choice Fold the example-flows content into the Install and run section as definition-style bullets. Each bullet leads with the user situation ("First-time user" / "Existing account") and shows the matching command. Drops the separate Example flows H3. Co-Authored-By: Claude Opus 4.7 (1M context) --- content/en/agentic_onboarding/setup.md | 35 ++++++++------------------ 1 file changed, 11 insertions(+), 24 deletions(-) diff --git a/content/en/agentic_onboarding/setup.md b/content/en/agentic_onboarding/setup.md index fa134400f3a..dd53a2a42e1 100644 --- a/content/en/agentic_onboarding/setup.md +++ b/content/en/agentic_onboarding/setup.md @@ -35,36 +35,23 @@ The CLI can: ### Install and run -Run the CLI with `npx`: +Choose the `npx` command that matches your situation: -```shell -npx @datadog/ai-setup-cli -``` +- **First-time user, or want to be walked through product selection**: Run the CLI with no arguments to step through account setup and product choice. -A browser window opens for authentication. After you complete the OAuth flow, return to your terminal. The CLI walks you through account setup and product selection, detects your project's frameworks, applies the required configuration, and provisions any necessary tokens. + ```shell + npx @datadog/ai-setup-cli + ``` -To skip product selection, pass `--product` with one of `error-tracking`, `rum`, `product-analytics`, `kubernetes`, `docker`, or `serverless`: +- **Existing account, know which product to install**: Pass `--product` to skip product selection. -```shell -npx @datadog/ai-setup-cli --product -``` + ```shell + npx @datadog/ai-setup-cli --product + ``` -### Example flows + Replace `` with one of `error-tracking`, `rum`, `product-analytics`, `kubernetes`, `docker`, or `serverless`. -**First-time user, no Datadog account yet:** - -```shell -npx @datadog/ai-setup-cli -# Prompts for account creation, then product selection. -``` - -**Existing account, instrumenting a local Terraform repo for Kubernetes:** - -```shell -cd my-k8s-terraform-repo -npx @datadog/ai-setup-cli --product kubernetes -# Detects Terraform, adds the Datadog Agent module, and writes the API key to .env. -``` +A browser window opens for authentication. After you complete the OAuth flow, return to your terminal. The CLI detects your project's frameworks, applies the required configuration, and provisions any necessary tokens. After the CLI completes, commit the changes to your repository and set any new environment variables (API keys, application IDs) in your production environment. Then see [Next steps](#next-steps) to confirm data is flowing. From 7107b9da31114aa4aeab7a2194d91bfe8af586cf Mon Sep 17 00:00:00 2001 From: Dominique Alessi Date: Wed, 13 May 2026 15:24:09 -0400 Subject: [PATCH 09/12] Tighten Install and run intro and add numbered post-run steps Drop the "matches your situation" framing, rephrase the two bullet labels for parallel state-plus-intent structure, and convert the post-bullet paragraphs into a three-step procedure. Co-Authored-By: Claude Opus 4.7 (1M context) --- content/en/agentic_onboarding/setup.md | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/content/en/agentic_onboarding/setup.md b/content/en/agentic_onboarding/setup.md index dd53a2a42e1..52c380cf913 100644 --- a/content/en/agentic_onboarding/setup.md +++ b/content/en/agentic_onboarding/setup.md @@ -35,15 +35,15 @@ The CLI can: ### Install and run -Choose the `npx` command that matches your situation: +Run the CLI with `npx`: -- **First-time user, or want to be walked through product selection**: Run the CLI with no arguments to step through account setup and product choice. +- **No Datadog account yet, or want to choose your product interactively**: Run with no arguments to step through account setup and product choice. ```shell npx @datadog/ai-setup-cli ``` -- **Existing account, know which product to install**: Pass `--product` to skip product selection. +- **Existing account, installing a specific product**: Pass `--product` to skip product selection. ```shell npx @datadog/ai-setup-cli --product @@ -51,9 +51,11 @@ Choose the `npx` command that matches your situation: Replace `` with one of `error-tracking`, `rum`, `product-analytics`, `kubernetes`, `docker`, or `serverless`. -A browser window opens for authentication. After you complete the OAuth flow, return to your terminal. The CLI detects your project's frameworks, applies the required configuration, and provisions any necessary tokens. +After you run the command: -After the CLI completes, commit the changes to your repository and set any new environment variables (API keys, application IDs) in your production environment. Then see [Next steps](#next-steps) to confirm data is flowing. +1. Complete the OAuth flow in your browser when prompted. After authentication, the CLI detects your project's frameworks, applies the required configuration, and provisions any necessary tokens. +1. Commit the changes to your repository and set any new environment variables (API keys, application IDs) in your production environment. +1. See [Next steps](#next-steps) to confirm data is flowing. ## MCP Server From e958db042ceb6bc4bdf734617c3fe2ca7503a5ff Mon Sep 17 00:00:00 2001 From: Dominique Alessi Date: Wed, 13 May 2026 15:26:07 -0400 Subject: [PATCH 10/12] Promote "Run the CLI" to step 1 of the procedure Fold the two command alternatives into step 1 as bold-prefixed continuation paragraphs. The whole Install and run section is now one four-step numbered procedure. Co-Authored-By: Claude Opus 4.7 (1M context) --- content/en/agentic_onboarding/setup.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/content/en/agentic_onboarding/setup.md b/content/en/agentic_onboarding/setup.md index 52c380cf913..e3f02b7c38f 100644 --- a/content/en/agentic_onboarding/setup.md +++ b/content/en/agentic_onboarding/setup.md @@ -35,15 +35,15 @@ The CLI can: ### Install and run -Run the CLI with `npx`: +1. Run the CLI with `npx`: -- **No Datadog account yet, or want to choose your product interactively**: Run with no arguments to step through account setup and product choice. + **No Datadog account yet, or want to choose your product interactively**: Run with no arguments to step through account setup and product choice. ```shell npx @datadog/ai-setup-cli ``` -- **Existing account, installing a specific product**: Pass `--product` to skip product selection. + **Existing account, installing a specific product**: Pass `--product` to skip product selection. ```shell npx @datadog/ai-setup-cli --product @@ -51,10 +51,10 @@ Run the CLI with `npx`: Replace `` with one of `error-tracking`, `rum`, `product-analytics`, `kubernetes`, `docker`, or `serverless`. -After you run the command: - 1. Complete the OAuth flow in your browser when prompted. After authentication, the CLI detects your project's frameworks, applies the required configuration, and provisions any necessary tokens. + 1. Commit the changes to your repository and set any new environment variables (API keys, application IDs) in your production environment. + 1. See [Next steps](#next-steps) to confirm data is flowing. ## MCP Server From 53b13ff19dcfd7fbb909a05eaac054b4929a1f9a Mon Sep 17 00:00:00 2001 From: Dominique Alessi Date: Wed, 13 May 2026 15:27:36 -0400 Subject: [PATCH 11/12] Restore team-wide rollout note in Next steps Bring back the secret-manager propagation guidance from the original draft. It's a distinct concern from the per-section deploy step (which only covers commit + production env vars) and fills out the Next steps section. Co-Authored-By: Claude Opus 4.7 (1M context) --- content/en/agentic_onboarding/setup.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/content/en/agentic_onboarding/setup.md b/content/en/agentic_onboarding/setup.md index e3f02b7c38f..1c0dd4b22b0 100644 --- a/content/en/agentic_onboarding/setup.md +++ b/content/en/agentic_onboarding/setup.md @@ -170,7 +170,8 @@ Skills work standalone, so you don't need the MCP Server installed to use them. ## Next steps -Confirm data is flowing in the Datadog UI: [APM > Services][6], [RUM > Applications][7], [Infrastructure > Hosts][8], or [Logs > Live Tail][9]. +- Confirm data is flowing in the Datadog UI: [APM > Services][6], [RUM > Applications][7], [Infrastructure > Hosts][8], or [Logs > Live Tail][9]. +- For team-wide rollout, propagate environment variables through your secret manager. [1]: /error_tracking/frontend/ [2]: /real_user_monitoring/ From 0aa7e3b5da4cc4d459413fbfa9a74b7faaee8d58 Mon Sep 17 00:00:00 2001 From: Dominique Alessi Date: Wed, 13 May 2026 15:32:08 -0400 Subject: [PATCH 12/12] Restructure Cursor install tab Lead with the recommended deeplink method and tuck the manual configuration into a collapse-content block. Matches the JetBrains tab pattern in bits_ai/mcp_server/setup.md. Co-Authored-By: Claude Opus 4.7 (1M context) --- content/en/agentic_onboarding/setup.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/content/en/agentic_onboarding/setup.md b/content/en/agentic_onboarding/setup.md index 1c0dd4b22b0..a2db0c997ec 100644 --- a/content/en/agentic_onboarding/setup.md +++ b/content/en/agentic_onboarding/setup.md @@ -79,21 +79,21 @@ In an active Claude Code session, run: {{% /tab %}} {{% tab "Cursor" %}} -Install the MCP Server using one of the following methods. +Click the install deeplink for your [Datadog site](/getting_started/site/), then click {{< ui >}}Install{{< /ui >}} in Cursor for the **datadog-onboarding-{{< region-param key="dd_datacenter_lowercase" >}}** server: -**Deeplink (recommended)**: Click the install deeplink for your [Datadog site](/getting_started/site/), then click {{< ui >}}Install{{< /ui >}} in Cursor for the **datadog-onboarding-{{< region-param key="dd_datacenter_lowercase" >}}** server: +
{{< region-param key="cursor_mcp_install_deeplink" >}}
- 
{{< region-param key="cursor_mcp_install_deeplink" >}}
+{{% collapse-content title="Manual configuration" level="h4" expanded=false %}} +Add the server to `~/.cursor/mcp.json`: -**Manual configuration**: Add the server to `~/.cursor/mcp.json`: - - 
{
+
{
   "mcpServers": {
     "datadog-onboarding-{{< region-param key="dd_datacenter_lowercase" >}}": {
       "url": "{{< region-param key="mcp_server_endpoint" >}}?toolsets=onboarding"
     }
   }
 }

+{{% /collapse-content %}}
 {{% /tab %}}
 
 {{% tab "Other MCP clients" %}}