Connect Datadog with Unblocked to connect alerts to recent changes

Datadog adds production evidence to engineering research: incidents describe impact, monitors expose alert conditions, and logs and metrics show what the system was doing. Unblocked connects those signals to code, pull requests, and team discussion so an agent can investigate beyond the symptom.

Monitoring context is reconciled with your code, pull requests, and discussions, so an investigation can connect a symptom to the recent change most likely to have caused it — not just describe the alert.

Once connected, any MCP-compatible coding agent — Claude Code, Cursor, Windsurf, GitHub Copilot, Codex — can pull this context through a single Unblocked MCP server connection.

What you get

• Incidents, logs, metrics, monitors, hosts — Unblocked references your Datadog telemetry when answering questions about outages, alerts, and production issues, and cites the resource it used.
• Symptom-to-change correlation — Because Datadog data sits alongside your code and pull requests, investigations connect an alert to the recent change most likely responsible.
• Read-only, region-aware connection — An API key and read-only application key connect your organization; you pick the Datadog region during setup.
• Cross-source synthesis — Datadog signals are combined with your code, pull requests, Sentry issues, and Slack threads into a single knowledge graph.

Need screenshots or troubleshooting?This is a concise connection summary. Follow the complete setup guide ↗

Prerequisites

• An Unblocked account (free to start).
• A Datadog API key and an application key with read-only scopes, plus your Datadog region.
• An MCP-compatible coding agent (Claude Code, Cursor, Windsurf, etc.) to use the context in your editor.

Step 1: Connect Datadog to Unblocked

1. In Unblocked, go to Settings → Data Sources → Connect another data source, and under Incident Management select Datadog.
2. In Datadog, create an API key (Organization Settings → API Keys).
3. Create an application key with the read-only scopes listed in the docs (events_read, incident_read, logs_read_data, timeseries_query, monitors_read, hosts_read, service-catalog read, user_access_read).
4. Paste both keys into Unblocked, select your Datadog region (US1 is the default), and click Next.

Step 2: Install the Unblocked MCP server

On macOS, one command auto-detects and configures your supported agents (Claude Code, Cursor, Windsurf, GitHub Copilot, Codex, VS Code):

The install script supports macOS only. On Windows or Linux, add the server manually using the configuration below, or follow the manual install guide ↗.

claude mcp add -s user --transport http unblocked https://getunblocked.com/api/mcpsse

{
  "mcpServers": {
    "unblocked": {
      "url": "https://getunblocked.com/api/mcpsse"
    }
  }
}

https://getunblocked.com/api/mcpsse

To give Claude Code, Cursor, GitHub Copilot, Codex, or another MCP-compatible AI coding agent access to Datadog context, connect Datadog to Unblocked and add the single Unblocked MCP server to your agent.

Unblocked acts as the MCP context layer for your Datadog data, searching incidents, logs, metrics, monitors, hosts alongside your other connected sources and returning cited results through these tools:

• context_researchMulti-source research across your Datadog incidents, logs, metrics, monitors, and hosts, plus your code, pull requests, and other connected sources. Returns a synthesized answer with citations back to the Datadog resource it used.
• context_get_urlsFetches the full content behind a Datadog resource URL your agent encounters — plus GitHub, Jira, Sentry, Slack, and more.

Questions you (or your agent) can ask Unblocked about your Datadog data:

• What recent change most likely caused this Datadog alert?
• Which deploy correlates with the latency spike on the checkout service?
• What do the logs show around the time of the last incident?
• Which monitors are currently alerting, and what changed recently?