Datadog links AI with real-time telemetry
Datadog launched MCP Server, connecting AI agents to real-time production telemetry, enabling automated rollback and immutable data snapshots reported.
The MCP Server aims to give AI agents controlled access to real-time observability data, including logs, metrics, and traces. This allows engineers to investigate and respond to production issues using AI agents while maintaining governance, security, and audit controls. It's now generally available as part of Datadog's AI-powered observability and security platform. The MCP Server feeds live logs, metrics, and traces directly into AI coding agents like Codex, Claude Code, and Cursor. This integration enables the investigation of production issues directly within the AI coding agent or IDE. Datadog's proactive detection and remediation signals can then be leveraged for automatic issue investigation and response. Datadog's MCP server acts as a bridge between Datadog and MCP-compatible AI agents, creating a layer on top of Datadog's endpoints. It derives intent from natural language prompts and determines if the prompt falls within its capabilities, making a call to the appropriate tool and endpoint. This simplifies data access for AI workflows by providing a dynamic protocol for agent communication.
