|
1 | 1 | --- |
2 | | -title: home |
| 2 | +title: Getting Started |
| 3 | +description: Set up pre-configured monitoring packages for your frontend, backend, or LLM application using agentic or manual setup. |
3 | 4 | type: studio |
4 | | -cascade: |
5 | | - type: studio |
6 | 5 | --- |
7 | 6 |
|
8 | | -Test |
| 7 | +## Overview |
| 8 | + |
| 9 | +Datadog Studio gives small development teams a streamlined observability platform to monitor, debug, and optimize their applications. Get started with pre-configured packages tailored to what you're building without any complex setup required. |
| 10 | + |
| 11 | +## How it works |
| 12 | + |
| 13 | +Datadog Studio provides pre-configured monitoring packages tailored to your application type. Select a package based on what you're building (frontend, backend, or LLM/AI), then use either **agentic setup**, where AI assistants like Cursor or Claude automatically configure your codebase, or **manual setup** for full control. After successfully configuring your package, your application sends telemetry data to Datadog, giving you immediate access to error tracking, performance monitoring, and analytics. |
| 14 | + |
| 15 | +## What's included |
| 16 | + |
| 17 | +Choose your package based on what you're building: |
| 18 | +| Application Type | Products Included | |
| 19 | +|------------------------|--------------| |
| 20 | +| Frontend applications | [Error Tracking][1], [Session Replay][2], [Product Analytics][3] | |
| 21 | +| Backend services | [Error Tracking][1], [Logs][4], [Metrics][5] | |
| 22 | +| LLMs / AI agents | [LLM Observability and AI Agent Monitoring][6] | |
| 23 | + |
| 24 | +## Sign up for Datadog Studio |
| 25 | + |
| 26 | +Before getting started, make sure you have an account with Datadog Studio. To create an account, go to [https://app.datadoghq.com/studio/signup][7]. |
| 27 | + |
| 28 | +## Setup |
| 29 | + |
| 30 | +Choose your setup method: |
| 31 | + |
| 32 | +- [Agentic setup](#agentic-setup): Let AI assistants ([Cursor][8] or [Claude][9]) automatically install and configure Datadog SDKs in your codebase. Only available for [specific platforms](#supported-platforms). |
| 33 | +- [Manual setup](#manual-setup): Follow step-by-step instructions to install and configure Datadog SDKs yourself. This method gives you full control over the integration. |
| 34 | + |
| 35 | +## Agentic setup |
| 36 | + |
| 37 | +### Supported platforms |
| 38 | +Agentic setup is available for the following platforms: |
| 39 | + |
| 40 | +**Frontend applications** |
| 41 | +- Next.js |
| 42 | +- React |
| 43 | +- Svelte |
| 44 | +- Vanilla JavaScript (Angular is not supported) |
| 45 | +- Vue |
| 46 | + |
| 47 | +**LLM and AI agent applications** |
| 48 | +- Python or Node.js—from scripts using [OpenAI's Responses API][10] to complex FastAPI applications powered by [LangGraph][11], or rich chatbot experiences built on [Vercel's AI SDK][12]. |
| 49 | + |
| 50 | +### Install the Datadog Onboarding MCP server |
| 51 | + |
| 52 | +To install the Datadog Onboarding Model Context Protocol (MCP) server: |
| 53 | + |
| 54 | +{{% collapse-content title="Cursor" level="h4" expanded=false id="cursor" %}} |
| 55 | + |
| 56 | +1. Copy the Cursor Deeplink into your browser based on your site region: |
| 57 | + |
| 58 | +{{< tabs >}} |
| 59 | +{{% tab "US1" %}} |
| 60 | +```sh |
| 61 | +cursor://anysphere.cursor-deeplink/mcp/install?name=datadog-onboarding-mcp&config=eyJ1cmwiOiJodHRwczovL21jcC5kYXRhZG9naHEuY29tL2FwaS91bnN0YWJsZS9tY3Atc2VydmVyL21jcD90b29sc2V0cz1vbmJvYXJkaW5nIiwidHlwZSI6Im9hdXRoIn0= |
| 62 | +``` |
| 63 | +{{% /tab %}} |
| 64 | + |
| 65 | +{{% tab "US3" %}} |
| 66 | +```sh |
| 67 | +cursor://anysphere.cursor-deeplink/mcp/install?name=datadog-onboarding-mcp&config=eyJ1cmwiOiJodHRwczovL21jcC51czMuZGF0YWRvZ2hxLmNvbS9hcGkvdW5zdGFibGUvbWNwLXNlcnZlci9tY3A/dG9vbHNldHM9b25ib2FyZGluZyIsInR5cGUiOiJvYXV0aCJ9 |
| 68 | +``` |
| 69 | +{{% /tab %}} |
| 70 | + |
| 71 | +{{% tab "US5" %}} |
| 72 | +```sh |
| 73 | +cursor://anysphere.cursor-deeplink/mcp/install?name=datadog-onboarding-mcp&config=eyJ1cmwiOiJodHRwczovL21jcC51czUuZGF0YWRvZ2hxLmNvbS9hcGkvdW5zdGFibGUvbWNwLXNlcnZlci9tY3A/dG9vbHNldHM9b25ib2FyZGluZyIsInR5cGUiOiJvYXV0aCJ9 |
| 74 | +``` |
| 75 | +{{% /tab %}} |
| 76 | +{{< /tabs >}} |
| 77 | + |
| 78 | +2. In Cursor, install the MCP, then click **Connect**. |
| 79 | +3. If prompted to open an external website, click **Open**. |
| 80 | +3. Confirm you see MCP tools listed for the `datadog-onboarding-mcp` server. |
| 81 | + |
| 82 | +{{% /collapse-content %}} |
| 83 | + |
| 84 | +{{% collapse-content title="Claude Code" level="h4" expanded=false id="claude-code" %}} |
| 85 | + |
| 86 | +1. Copy and execute the Claude Code command into your terminal: |
| 87 | + |
| 88 | +{{< tabs >}} |
| 89 | +{{% tab "US1" %}} |
| 90 | +```sh |
| 91 | +claude mcp add --transport http datadog-onboarding-mcp "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp?toolsets=onboarding" && claude /mcp |
| 92 | +``` |
| 93 | +{{% /tab %}} |
| 94 | + |
| 95 | +{{% tab "US3" %}} |
| 96 | +```sh |
| 97 | +claude mcp add --transport http datadog-onboarding-mcp "https://mcp.us3.datadoghq.com/api/unstable/mcp-server/mcp?toolsets=onboarding" && claude /mcp |
| 98 | +``` |
| 99 | +{{% /tab %}} |
| 100 | +{{< /tabs >}} |
| 101 | + |
| 102 | +2. Start a Claude Code session and execute the `/mcp` command inside the session. |
| 103 | +3. Select the MCP server you added and press **Enter** to login. |
| 104 | + |
| 105 | +{{% /collapse-content %}} |
| 106 | + |
| 107 | +### Set up your project |
| 108 | + |
| 109 | +Prompt your AI coding agent to enable all capabilities (Error Tracking, Session Replay, Product Analytics, and LLM Observability) in minutes by copying the below prompt into Cursor or Claude Code. |
| 110 | + |
| 111 | +**Prompt**: |
| 112 | +```console |
| 113 | +Add Datadog Studio to my project |
| 114 | +``` |
| 115 | + |
| 116 | +When you give this prompt to your coding agent, it does the following: |
| 117 | + |
| 118 | +- Analyze your project and identify if the MCP server offers a tool that can be used to set it up with Datadog |
| 119 | +- Call the tool (asking for your permission before doing so) with inferred parameters from your project (for example: your project's framework, language, and bundler) |
| 120 | +- Follow the instructions the MCP tool provides as context to your coding agent, making code changes on your behalf (don't worry - Datadog does not commit them) |
| 121 | +- Provide testing steps to confirm that your application is correctly configured to send telemetry to Datadog |
| 122 | + |
| 123 | +### Deploying to production |
| 124 | + |
| 125 | +Depending on how your application is deployed, you need to commit the changes and set or upload provided environment variables to your production environment. |
| 126 | + |
| 127 | +## Manual setup |
| 128 | + |
| 129 | +If you prefer manual setup, follow the in-app instructions for each product in your selected package. You can either choose manual setup from the Getting Started page or by adding a New Application from the homepage. |
| 130 | + |
| 131 | +### Frontend monitoring |
| 132 | +- [Frontend Error Tracking][13] |
| 133 | +- [Session Replay][14] |
| 134 | +- [Product Analytics][15] |
| 135 | + |
| 136 | +### Backend monitoring |
| 137 | +- [Backend Error Tracking][17] |
| 138 | +- Logs from: |
| 139 | + - [Servers / VMs][18] |
| 140 | + - [Containers][19] |
| 141 | + - [Cloud / Integrations][20] |
| 142 | + - [Applications][21] |
| 143 | + - [APIs][22] |
| 144 | +- Metrics: |
| 145 | + - [Custom metrics][23] |
| 146 | + - [OpenTelemetry][24] |
| 147 | + - [Integrations][25] |
| 148 | + |
| 149 | +### LLM Observability |
| 150 | +- [LLM Observability][16] |
| 151 | + |
| 152 | +[1]: /studio/error_tracking/ |
| 153 | +[2]: /studio/session_replay/ |
| 154 | +[3]: /studio/product_analytics/ |
| 155 | +[4]: /studio/logs/ |
| 156 | +[5]: /studio/metrics/ |
| 157 | +[6]: /studio/llm_observability/ |
| 158 | +[7]: https://app.datadoghq.com/studio/signup |
| 159 | +[8]: https://cursor.com/ |
| 160 | +[9]: https://claude.ai/ |
| 161 | +[10]: https://platform.openai.com/docs/guides/text |
| 162 | +[11]: https://github.com/langchain-ai/langgraph |
| 163 | +[12]: https://github.com/vercel/ai-chatbot |
| 164 | +[13]: /studio/error_tracking/frontend |
| 165 | +[14]: /studio/real_user_monitoring/session_replay/ |
| 166 | +[15]: /studio/product_analytics/#getting-started |
| 167 | +[16]: /studio/llm_observability/quickstart/?tab=python#trace-an-llm-application |
| 168 | +[17]: /studio/error_tracking/backend/getting_started/ |
| 169 | +[18]: /studio/logs/log_collection/?tab=host |
| 170 | +[19]: /studio/logs/log_collection/?tab=container |
| 171 | +[20]: /studio/logs/log_collection/?tab=cloudintegration |
| 172 | +[21]: /studio/logs/log_collection/?tab=application |
| 173 | +[22]: /studio/api/latest/logs/ |
| 174 | +[23]: /studio/metrics/custom_metrics/ |
| 175 | +[24]: /studio/metrics/open_telemetry/ |
| 176 | +[25]: https://app.datadoghq.com/integrations |
0 commit comments