# Your Datadog alerts. The story behind them.

Source: https://corespeed.io/integrations/datadog

Connect Datadog to Claude Code, Codex, Cursor or any MCP agent through CoreSpeed. Your agent searches monitors, logs, traces and incidents, and turns an alert into a timeline with its likely cause. CoreSpeed proxies Datadog's own MCP server for US1 accounts; access follows your Datadog role, and changing a monitor or dashboard is a separate call.

## Set up an agent

Give your agent this line: `set up https://corespeed.io/SKILL.md (read it raw, e.g. with curl)`

It fetches the skill at https://corespeed.io/SKILL.md, adds the CoreSpeed MCP server, signs you in (or up), and keeps the skill for next time. Connect Datadog after setup. Access follows the connected account and its permissions. Create an account: https://app.corespeed.io/sign-up

## Know what fired. Know why

Ask your agent which monitors are alerting, what the logs say around them, and what changed first.

You ask your agent: "Which production monitors are alerting right now? For the worst one, read the error logs from the last 20 minutes and tell me the likely cause. Do not change any monitor."

It calls CoreSpeed:

- `datadog__search_datadog_monitors`: ok, 655 ms
- `datadog__search_datadog_logs`: ok, 1184 ms

It reads from: Datadog.

### Alert summary: Latency, from one deploy.

Checkout latency alerted at 14:05. The logs show the database pool running out right after deploy v2.41.

**Likely cause**

- Deploy v2.41 lowered the database pool size.

**Next step**

- Restore the pool size, then watch p95 latency.

_Illustrative example · Fictional services · No monitors changed_

All connectors: https://corespeed.io/docs/connectors

## From an alert to what happened

Requests you can make once Datadog is connected. The data is fictional.

### See what is alerting

Monitors · production · Triggered and warning

- Alert: checkout p95 latency above 2 s
- Warn: Queue depth on the email worker
- From the monitors you can see

### Read the logs around it

checkout · 14:02 to 14:20 · Errors, grouped

- Most frequent: Connection pool exhausted
- First seen: 14:03, right after the deploy
- Read, not changed

### Write the incident timeline

Checkout latency · draft · Monitors, logs and the incident

- Started: 14:03, after deploy v2.41
- Likely cause: A smaller database pool
- A draft for the postmortem

## Keep your agent. Bring your work

One CoreSpeed account, across compatible agents.

1. **Set up CoreSpeed**: Give your agent the setup line. It adds CoreSpeed and signs you in.
2. **Connect Datadog**: Authorize the account and the content you need.
3. **Start with one task**: Ask for a summary, a brief, or a draft. Review the answer.

Setup guides: Claude Code https://corespeed.io/docs/mcp#claude-code · Codex https://corespeed.io/docs/mcp#codex · Cursor https://corespeed.io/docs/mcp#cursor

## Questions

### Which Datadog sites are supported?

US1 today. The connector proxies Datadog's own MCP server for US1 accounts.

### Can my agent see data my Datadog role cannot?

No. Datadog checks your own role and product permissions on every call.

### Does this change anything on its own?

No. Searching is separate from writing. Changing a monitor, dashboard or workflow is its own tool call, which approvals can hold for a person.

### Do I have to switch agents?

No. CoreSpeed adds tools to the agent you already use: Claude Code, Codex, Cursor, or another MCP client. Each one signs in once.

### Can my agent access every account in our organization?

No. Access follows your CoreSpeed identity, each connection's visibility, and the app's own permissions. Personal connections stay private.

### Does this work without connecting an account?

No. Connect the app's account first; your CoreSpeed workspace shows what each app needs. The examples on this page use fictional data. All connectors: https://corespeed.io/docs/connectors

Every tool and price: https://corespeed.io/catalog/datadog

## Related pages

- [MCP gateway for your agents and tools](https://corespeed.io/solutions/mcp-gateway): Reach connected apps, built-in tools, and your own remote MCP servers through one authenticated CoreSpeed MCP endpoint.
- [Sentry for Claude Code, Codex, and Cursor](https://corespeed.io/integrations/sentry): Bring Sentry issues, events and stack traces into your agent. Find the error that matters and the likely cause.
- [Shared agent tools and controls for teams](https://corespeed.io/solutions/teams): Manage shared connections, approval policies, and tool usage for teams working across Claude Code, Codex, and other MCP clients.

## Sources

- Connectors: https://corespeed.io/docs/connectors
- Datadog MCP Server: https://docs.datadoghq.com/mcp_server/
- Set up the Datadog MCP Server: https://docs.datadoghq.com/mcp_server/setup/
- Datadog monitors: https://docs.datadoghq.com/monitors/

Reviewed 2026-11-10.

## Links

- Product overview: https://corespeed.io/ (Markdown: https://corespeed.io/index.md)
- All integrations: https://corespeed.io/integrations (Markdown: https://corespeed.io/integrations.md)
- Documentation: https://corespeed.io/docs
- Pricing: https://corespeed.io/pricing (Markdown: https://corespeed.io/pricing.md)