Snowflake releases AI-agent tools for observability data

Snowflake announced the general availability of a redesigned Observe MCP server and new Observe CLI, both tools built to make observability data accessible to AI agents as well as human engineers. The company recognized a fundamental shift in how telemetry is consumed: coding assistants can now investigate errors before an engineer opens a ticket, and AI site reliability engineers (SREs) can correlate failures across services without human intervention. This places new demands on observability platforms because observability must work for both humans interacting with data through a UI and agents using programmatic interfaces like APIs, model context protocol (MCP), and command line interface (CLI).

The previous Observe CLI covered only a narrow slice of the platform's functionality, as most capabilities were inaccessible from the terminal. The new CLI provides programmatic access to the entire Observe platform, with the same surface area available through the MCP server and the UI. It works in agent environments like Claude Code as well as interactive terminal sessions. Some workflows run autonomously in the background, handling routine tasks without an engineer present, while others are designed for interactive use requiring direct human guidance during incident investigations.

The most significant technical change is architectural. The original MCP server included a custom LLM harness that received user queries, performed reasoning, and returned answers. With advances in foundation models, Snowflake determined this LLM intermediary was no longer necessary. The new architecture removes it entirely, eliminating the expense of passing queries through Observe's own LLM before agents could access data. Instead, agents now connect directly to Observe's APIs and context graph, giving them direct visibility into the data structure, permission to explore datasets, and the ability to write efficient OPAL queries. This design reduces both latency and operational cost for both Snowflake and its customers.

Both the CLI and MCP server ship with a library of prebuilt skills—structured workflows built based on how Observe engineers solve common observability tasks. Agents and engineers can use these skills immediately to investigate incidents, trace failures, validate changes, find n+1 issues, and detect outliers, with no additional setup required after configuration. 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. General availability is rolling out now across all clusters, with eu-2 and ca-1 regions to follow shortly.