What happened
Snowflake announced general availability of a redesigned Observe MCP (model context protocol) server and a new Observe CLI with full parity to the MCP. The new MCP server removes a custom LLM intermediary layer, allowing agents to connect directly to Observe's APIs and access the same capabilities available in the UI, including APM service maps, OpenTelemetry data collection setup, and active alert listing. The CLI provides programmatic access to Observe's full platform from the command line and works in agent environments like Claude Code as well as interactive terminal sessions.
Why it matters
Observability platforms must now serve both humans and AI agents, not just people reading dashboards. Engineers are building custom alert-triage agents that automatically query Observe when alerts fire, and copilots that assist during incident investigations. By removing the LLM intermediary, the new architecture cuts latency and operating costs for every agent query, while giving agents direct visibility into Observe's data structure so they can determine which data sets to query and write efficient observability queries.
What to watch
Both the MCP server and CLI ship with prebuilt skills—structured workflows for common observability tasks like investigating incidents, tracing failures, validating changes, finding n+1 issues, and detecting outliers. These skills work immediately after configuration without additional setup. General availability is rolling out now across all clusters; eu-2 and ca-1 regions will follow shortly.
Summaries like this, in your inbox every morning.
The shift toward AI agents consuming observability data represents a fundamental change in how teams debug and monitor production systems. Previously, telemetry platforms were designed for human operators reading dashboards and dashboards; now agents must be able to programmatically query and reason about operational data at scale. Snowflake's redesign responds directly to this: by removing the LLM intermediary that was built into the original Observe MCP server, the company reduces both the latency and the operational cost of every agent query, while giving agents direct access to Observe's APIs and data structure.
The introduction of the CLI with full parity to the MCP server addresses a concrete developer need. The previous Observe CLI covered only a narrow slice of the platform; most functionality was inaccessible from the terminal. Engineers had built workarounds to fill this gap, and some teams had even constructed their own custom integrations. The new agent-compatible CLI removes this friction by exposing the entire Observe platform—including the ability to update dashboards after an investigation, fetch chart images for automated reports, and query APM errors directly—through both programmatic and interactive interfaces. The prebuilt skills for common observability workflows (incident investigation, failure tracing, change validation, n+1 detection, and outlier detection) lower the barrier to entry: both humans and machines can begin using these workflows immediately after configuration, without custom development.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
Amazon introduced Bee Frontier, a wearable personal AI, for $74.99 in Onyx, Lavender and Sage, and Bee Eclipse…
Citi has become the latest US bank to restrict AI agents from accessing accounts, per the Financial Times
Dell says its AI Data Platform uses a four-engine architecture and a Unified Semantic Layer to connect siloed…
Microsoft and Nvidia are promoting RTX Spark, a new class of Windows PCs for local AI, with a top configuratio…
Microsoft AI CEO Mustafa Suleyman told employees that MAI-Base-2, announced Thursday, is a stronger pre-traine…
Aparna Nair, IBM's chief talent, leadership, and culture officer, said generalists alone "will cut it" in the…
