Snowflake's Observe Launches MCP Server and CLI for AI Agents

Snowflake announced general availability of a redesigned Observe MCP server and a new Observe CLI, both available rolling out now across all clusters with eu-2 and ca-1 to follow shortly. The two tools offer full operational parity: every operation the MCP server exposes to agents is also available as a CLI command, enabling engineers to choose the interface that fits their workflow—whether connecting custom AI agents, interacting directly from the terminal, or building copilots for incident investigations.

The redesigned architecture represents a significant departure from the original Observe MCP. In the previous version, agents sent queries to a single endpoint where Observe's built-in LLM interpreted the question and returned an answer. This design meant agents lacked direct visibility into Observe's data structure, couldn't explore datasets autonomously, and incurred latency and cost overhead for every interaction. The new MCP server removes the LLM intermediary entirely. Agents now connect directly to Observe's APIs—the same APIs that power Observe's frontend—and can query Observe's context graph themselves. This allows agents to determine which datasets are most valuable to query, write efficient OPAL (Observe's query language), and run precise observability queries against any telemetry data without the latency or cost penalty of the old architecture.

Both the CLI and MCP server ship with a library of prebuilt skills: structured workflows built on how Observe engineers solve common observability tasks. These skills cover incident investigation, failure tracing, change validation, n+1 issue detection, and outlier detection. Both humans and agents can use these skills immediately after configuration without additional setup. Engineers are already using the tools to build custom alert-triage agents that automatically query Observe when an alert fires and pull production telemetry for debugging context, and copilots that work alongside humans during incident investigations. Some workflows run autonomously in the background to handle routine tasks, while others are designed for interactive use where an engineer guides the investigation directly. The new CLI provides programmatic access from agent environments like Claude Code as well as interactive terminal sessions, helping users compose, automate, and extend their observability workflows. Through the MCP server, agents have access to the same capabilities available in the Observe UI: APM service maps, OpenTelemetry data collection setup, and active alert listing.