Gleap AI agents can use Datadog through Composio, for engineering and support teams that monitor production in Datadog and hear about problems from customers in Gleap. Kai Code, Kai Support and custom agents can search logs and traces around a bug report and check whether a monitor or incident already covers it.
What a Gleap agent can do in Datadog
- Logs around a report: Search logs finds log lines for the account or request around the time a Gleap bug report arrived.
- Slow or failing requests: Search Traces finds the traces for the endpoint the customer used, so a slow page has a concrete cause to look at.
- Is it already known: List monitors and List Incidents show whether a monitor is alerting or an incident is open, so support can tell customers the team is on it.
- Production evidence for a fix: with Datadog in Kai Code’s MCP settings, Kai Code can query logs and metrics while it prepares a pull request for your engineers to review.
- Customer impact on the timeline: Create event adds an event to Datadog when several customers report the same problem in Gleap.
Example: reports export timing out
Customers report through the Gleap widget that the reports export spins and then fails. A teammate asks a custom agent on one of the tickets to check Datadog. The agent searches traces for the export endpoint, finds requests timing out at the database since this morning and sees an open monitor alert for the same service. It posts both on the Gleap ticket, and the on-call engineer decides whether this becomes an incident while support tells customers the issue is known.
How to connect Datadog
- In Gleap, open Kai Code, click Settings and open MCP.
- Click Add MCP server, search for “Datadog” and select it.
- Click Connect Datadog and follow the authorization Gleap shows: Datadog API credentials, or the client ID and secret of your own Datadog OAuth app.
- Open the Datadog server and switch off the tools Kai Code should not call, such as Delete monitor, Mute Monitor, Create downtime and Submit metrics.
- For a custom agent, add Datadog under the agent’s Tools with Add tool instead, then publish and test it.
Kai Code is on Team, Pro and Enterprise, and Kai Support can use connected apps as tools on the same plans. Custom agents are on the Team, Pro and Enterprise plans.
FAQ
Does Gleap integrate with Datadog?
Yes. Kai Code, Kai Support and custom agents use Datadog through Composio’s Datadog toolkit, which supports OAuth, bearer tokens and API keys. They query Datadog while they run; Gleap does not ingest logs or metrics.
Does Gleap connect to Datadog through MCP?
Yes. Gleap connects to Composio’s MCP server for Datadog with the Datadog account you connect, and the agent calls only the actions you leave switched on. To use a different remote MCP server, add it by URL: as a Custom MCP tool for Kai Support or a custom agent, or as a custom HTTP server in Kai Code.
What can a Gleap AI agent do in Datadog?
It can search logs, traces and spans, query metrics, read monitors, incidents, dashboards, services, hosts and SLOs, create events, monitors, dashboards and synthetic tests, and mute monitors or schedule downtime. Muting and downtime hide alerts, so keep them with your on-call engineers.
Which Gleap plan includes the Datadog integration?
Kai Code and Kai Support’s investigations can use Datadog on Team, Pro and Enterprise, and Kai Support can use connected apps as tools in its customer conversations on the same plans. Custom agents that use Datadog are part of the Team, Pro and Enterprise plans. The Datadog key’s permissions decide which data the agents can read. AI usage is billed separately; see pricing.
Can we keep customer data out of the agent’s Datadog queries?
The agent sees whatever the connected Datadog credentials can read. Use a key scoped to the logs and services the agent needs, and keep sensitive fields masked in Datadog itself.
