Snowflake Observe adds CLI and redesigned MCP for AI agents to access telemetry directly

Snowflake announced general availability of a redesigned Observe MCP server and a new Observe CLI on a rolling basis across all clusters, with eu-2 and ca-1 regions following shortly. Both tools are built to enable observability to work for both humans and AI agents, addressing a new reality: agents have a sophisticated understanding of operational data and may no longer be the primary readers of telemetry.

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

Both the CLI and MCP server ship with a library of prebuilt skills—structured workflows based on how Observe engineers solve common observability tasks. Agents and engineers can use these skills to investigate incidents, trace failures, validate changes, find n+1 issues, and detect outliers without additional setup after configuration. The most significant change in the rebuilt MCP server is architectural and economic. The original MCP had a custom LLM harness: it received a user query, handled the reasoning, and returned an answer. With advances in foundation models, Snowflake determined that an Observe LLM middleman was no longer necessary. The new architecture drops it, removing the need to pass on that operational cost. In the old design, agents sent queries to a single endpoint where Observe's LLM interpreted the question, leaving agents without direct visibility into data structures and without permission to explore datasets—an expensive arrangement for both Observe and customers. The new MCP server lets agents connect directly to the Observe platform and access the same APIs that power Observe's frontend. Agents can now query Observe's context graph directly, determine which datasets are most valuable to query for more accurate answers, and write efficient OPAL queries. Through the MCP server, agents have access to APM service maps, OpenTelemetry data collection setup in Observe, and active alert listing. Engineering teams are already using these 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. To get started, users log into their tenant, go to "Manage account" → "MCP server details", and follow setup instructions for their agent of choice.