What an agent can do in Datadog
Investigate production with Datadog: search logs, metrics, traces, monitors, incidents and dashboards. US1 site; add another site as a custom server.
Jobs on Rush that use Datadog
- Find Noisy Datadog Monitors
- Build an SLO Report From Datadog
- Write a Weekly Incident Summary From Datadog
- Fix an ASP.NET Core App Bug From a Datadog Monitor Alert
- Fix a Django App Bug From a Datadog Monitor Alert
- Fix an Express API Bug From a Datadog Monitor Alert
- Fix a FastAPI App Bug From a Datadog Monitor Alert
- Fix a Go Service Bug From a Datadog Monitor Alert
- Fix a Laravel App Bug From a Datadog Monitor Alert
- Fix a NestJS API Bug From a Datadog Monitor Alert
- Fix a Phoenix App Bug From a Datadog Monitor Alert
- Fix a Rails App Bug From a Datadog Monitor Alert
- Fix a Spring Boot App Bug From a Datadog Monitor Alert
- Investigate an ASP.NET Core App Incident With Datadog
- Investigate a Django App Incident With Datadog
- Investigate a Go Service Incident With Datadog
- Investigate a NestJS API Incident With Datadog
- Investigate a Rails App Incident With Datadog
- Investigate a Spring Boot App Incident With Datadog
- Investigate Thread Pool Starvation in an ASP.NET Core App
How Datadog connects
Datadog is a remote MCP server, published by Datadog, at https://mcp.datadoghq.com/api/unstable/mcp-server/mcp. Connecting it signs in through the MCP OAuth flow on Datadog's side.
From Datadog: Datadog's MCP documentation.
Connect it once in the console under Settings → Connections, or from your server with POST /me/connections. The sign-in finishes in a browser signed in to the console as the same person, and a link not finished within 10 minutes expires.
After that, a run that names datadog in connections, or runs a saved agent that names it, gets it; your connections reach no run that does not name them.
POST https://api.phoenix.so/me/connections
{
"type": "mcp",
"name": "Datadog",
"url": "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"
}Whose Datadog account the agent uses
Your Datadog connection is personal: it belongs to the person who signed in. A run started in the console uses that person's Datadog, and a run started with an API key uses the Datadog of the member who created the key.
To act for your own app's users, make each user an agent from your template and show them, signed in to your app, the sign-in link POST /o/{org}/agents/{agent}/connections returns. They sign in to their own Datadog, and that agent's runs use their account and nothing else: never yours, never another user's.
More Observability integrations
Frequently asked questions
How do I connect Datadog to Rush?
Open Settings → Connections in the console and connect Datadog, or send POST /me/connections with {"type":"mcp","name":"Datadog","url":"https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"} and open the authorize_url it returns while signed in to the console. The connection reads pending until the sign-in finishes, then connected.
Does every run get my Datadog account?
No. A run gets your Datadog connection only when it names it in connections ("connections": ["datadog"]), or runs a saved agent that names it. A saved agent names its connections once, and every run of it gets them.
What can an agent do in Datadog?
Investigate production with Datadog: search logs, metrics, traces, monitors, incidents and dashboards. US1 site; add another site as a custom server. 20 published jobs use it; this page lists them.
Can my app's users connect their own Datadog?
Yes. Make each user an agent from your template, and they sign in to their own Datadog through the link POST /o/{org}/agents/{agent}/connections returns. That agent's runs use their account alone.
Keep reading
- AI agents for engineering teams: every job and app for them
- How connections work: sign in once, then every run that names a connection gets it
- Start your first run from the developer API quickstart
- Pricing: one price per member, hours shared by the team
- How Rush compares with other cloud agents
- Every app and MCP server Rush connects to