Build and troubleshoot Observability Pipelines with AI agents
Blog post from Datadog
Datadog’s Observability Pipelines tools are now generally available through its MCP Server, allowing AI agents in clients such as Claude Code, Cursor, Codex, and VS Code to work with pipeline configurations and metrics. Agents can discover supported components, draft and validate pipelines from natural-language requests, inspect pipeline health and event-flow metrics, review proposed changes, and measure how filters or predefined packs affect log volume. These capabilities support tasks such as routing and redacting new log sources, diagnosing errors or dropped events, testing configuration changes, and checking whether volume reductions caused unintended losses. Deployment remains under team control: agents cannot modify or delete existing pipelines, newly created pipelines do not process data until a Worker is installed, validation can happen before creation, and access is limited by the connected user’s permissions. Teams can enable the core and observability-pipelines toolsets in a supported MCP client to get started.
| Trend | Post Mentions | Total Month Mentions | Posts | Companies | MoM |
|---|---|---|---|---|---|
| Observability | 18 | 2,390 | 523 | 156 | -23% |
| MCP | 10 | 9,757 | 959 | 203 | -18% |
| AI Agents | 4 | 6,233 | 1,230 | 245 | -11% |
| Datadog MCP Server | 4 | 19 | 6 | 1 | +375% |
Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.