# Datadog for AI agents. Managed auth, ready-made tools.

> Search logs, query metrics, check monitors and incidents, and schedule downtimes in your users' Datadog organizations.

- Page: https://www.agent200.com/tools/datadog/
- Category: Developer tools
- Authentication: Managed OAuth
- Identifier in code: `datadog`
- Create an API key: https://agent200.com/platform/apikeys/
- Updated: 2026-11-15

## Instructions for AI agents

Connector: Datadog, through Agent200. In code: "datadog".
What it does: Search logs, query metrics, check monitors and incidents, and schedule downtimes in your users' Datadog organizations.
Page: https://www.agent200.com/tools/datadog/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Sign-in is managed OAuth. Each end user approves access once, on Datadog's own page, through the authorization link Agent200 returns. Never ask a user for a Datadog password or token in chat.
3. Give every request a stable id for the end user. Agent200 uses only that user's own connection.
4. Read tools: datadog_search_logs, datadog_query_metrics, datadog_list_monitors, datadog_search_events, datadog_list_incidents. Write tools: datadog_create_downtime, datadog_create_incident. Name "datadog" in the tools of a request; the model decides which tool to call.
5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
6. Before a write, confirm with the user, unless they asked for that exact change.
7. For setup with a specific framework, follow its guide:
   https://www.agent200.com/tools/datadog/framework/claude/
   https://www.agent200.com/tools/datadog/framework/chatgpt/
   https://www.agent200.com/tools/datadog/framework/claude-code/
   https://www.agent200.com/tools/datadog/framework/muse/
   https://www.agent200.com/tools/datadog/framework/grok-bot/
   https://www.agent200.com/tools/datadog/framework/openai-dots/
   https://www.agent200.com/tools/datadog/framework/claude-duet/
   https://www.agent200.com/tools/datadog/framework/hermes-agent/
   https://www.agent200.com/tools/datadog/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## About

With the Datadog connector, your agent investigates in each user's own Datadog organization through Agent200: it searches logs, queries metrics, checks monitors, events and incidents, and can schedule a downtime or open an incident. Every user connects their own account through managed OAuth.

Datadog is an observability platform that brings metrics, logs, traces and alerts from your infrastructure and applications into one place.

## Datadog tools

- **Search logs** (`datadog_search_logs`, read): Find log events that match a query in a time range.
- **Query metrics** (`datadog_query_metrics`, read): Read timeseries points for a metric query.
- **List monitors** (`datadog_list_monitors`, read): List monitors and their current state.
- **Schedule a downtime** (`datadog_create_downtime`, write): Silence alerts from chosen monitors for a period.
- **Search events** (`datadog_search_events`, read): Find events such as deploys and alerts in a time range.
- **List incidents** (`datadog_list_incidents`, read): List incidents with their severity and state.
- **Create an incident** (`datadog_create_incident`, write): Declare an incident with a title and severity.

## Limits you can set

**Turn single tools on or off.** Let your agent search logs and metrics, and switch off `datadog_create_downtime` and `datadog_create_incident` if it should observe but never act.

**Restrict what the agent reaches.** Choose the endpoints and scopes a project may use. A call outside them is refused.

## Get started

### Step 1: Set up the SDK

Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Let your user connect Datadog

Each end user authorizes their own Datadog account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own Datadog account, once.
const connection = await agent200
  .user("user_123")
  .connect("datadog");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 3: Run with the Datadog tools

Name the user, the model and the tools. The model decides which Datadog tools to call, and Agent200 executes them with that user's connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "Which monitors are alerting right now",
    tools: ["datadog"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Sign-in and permissions

**Who signs in.** Each of your users, once, on Datadog's own page. You never see or store their Datadog password.

**What access is requested.** Datadog lists the scopes requested, such as reading logs, metrics and monitors. The user must already hold the Datadog permissions for each scope, so the agent never gets more than that user has.

## Example requests

- "Which monitors are alerting right now"
- "Show me the 500 errors from the checkout service in the last hour"
- "What was p95 latency on the API yesterday"
- "Mute the staging monitors during tonight's maintenance"

## Guides: Datadog with your AI framework

- [Datadog + Claude](https://www.agent200.com/tools/datadog/framework/claude.md): Connect Datadog to Claude through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Datadog + ChatGPT](https://www.agent200.com/tools/datadog/framework/chatgpt.md): ChatGPT cannot send an API key to a custom MCP server, so this guide builds Datadog into your own agent with OpenAI's models and the Agent200 SDK.
- [Datadog + Claude Code](https://www.agent200.com/tools/datadog/framework/claude-code.md): Have Claude Code build a Datadog agent with the Agent200 SDK: managed OAuth, ready-made tools and one API key.
- [Datadog + Muse](https://www.agent200.com/tools/datadog/framework/muse.md): Connect Datadog to Muse through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Datadog + Grok Bot](https://www.agent200.com/tools/datadog/framework/grok-bot.md): Connect Datadog to Grok Bot through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Datadog + OpenAI Dots](https://www.agent200.com/tools/datadog/framework/openai-dots.md): Dots cannot send an API key to a custom MCP server, so this guide builds an always-on Datadog agent with OpenAI's models and the Agent200 SDK.
- [Datadog + Claude Duet](https://www.agent200.com/tools/datadog/framework/claude-duet.md): Connect Datadog to Claude Duet through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Datadog + Hermes Agent](https://www.agent200.com/tools/datadog/framework/hermes-agent.md): Connect Datadog to Hermes Agent through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Datadog + OpenClaw](https://www.agent200.com/tools/datadog/framework/openclaw.md): Connect Datadog to OpenClaw through Agent200's MCP server: managed OAuth, ready-made tools and one API key.

## FAQ

### Who handles the Datadog OAuth flow and the tokens?

Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Datadog.

### Does my agent act as the end user?

Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Datadog connection, never another user's. It cannot reach anything the user or Datadog has not authorized.

### Can I limit what my agent can do in Datadog?

Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.

## Related connectors

- [GitHub](https://www.agent200.com/tools/github.md): Read repositories and work with issues and pull requests as the connected user.
- [GitLab](https://www.agent200.com/tools/gitlab.md): Review merge requests, file issues, read code and check pipelines in your users' GitLab projects.
- [Bitbucket](https://www.agent200.com/tools/bitbucket.md): List and open pull requests, comment, read code and check pipelines in your users' Bitbucket workspaces.
- [Jira](https://www.agent200.com/tools/jira.md): Search, create and transition Jira issues for the connected user.

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
