The MC Agent Toolkit now includes a monitor creation skill that guides coding agents through correctly creating Monte Carlo monitors via MCP. The skill enforces a validate-then-create workflow: confirm the target table exists, verify field names and types, then build the monitor with the correct parameters.

Supported monitor types include metric, validation, comparison, custom SQL, and table monitors. If you have the latest mc-agent-toolkit plugin installed, the skill is already available.

Monte Carlo's GitHub integration now includes two agentic guardrails completing the code review and merge gate stages of MC Prevent.

PR Agent automatically posts a risk assessment on every pull request, covering affected tables, downstream blast radius, and active alerts, the moment a PR is opened. Comment mc review on any PR to re-trigger an assessment.

CI Agent is an optional GitHub Action (and CircleCI orb) that converts the PR Agent's assessment into a pass, warn, or fail verdict posted as a GitHub Check Run. It ships in warn-only mode by default; switch to fail-on-high-risk to block high-risk merges via branch protection. Add mc-override to any PR to bypass the gate, with all overrides logged.

Existing GitHub integration customers need to reauthenticate to use the new features. CI Agent requires PR Agent.

Learn more here: https://docs.getmontecarlo.com/docs/github

You can now run individual validation tests directly from the integration settings page. Select any specific test to execute it on its own, making it faster to verify specific permissions when troubleshooting integration configurations.

The Safe Change plugin for Claude Code now enforces impact assessments before any SQL model edit. When your AI editor touches a dbt model, the plugin automatically pulls Monte Carlo context -- table health, alerts, lineage, and blast radius -- and uses it to shape safer code suggestions.

New in this release: a validate command lets you generate and run validation queries on demand, turn-end prompts encourage validation before moving on, and a commit gate proactively surfaces validation queries and monitor gaps before you push changes.

You can now adjust monitor sensitivity directly from the Monitors list in bulk. Select one or more monitors, choose a sensitivity level, and apply the change in seconds.

Supported for Metric, Custom SQL, and Agent Metric monitors using automated thresholds.

The Monitoring Agent now draws on criticality data across your warehouse to better prioritize monitoring recommendations. It can identify monitoring gaps directly within the agent workflow, surfacing unmonitored areas so you can act on them in context.

Monitor suggestions have expanded to include metric, validation, and custom SQL monitors. You can review recommendations and create monitors directly from the agent feed.

Network Access Controls (NAC) now extend to the Monte Carlo UI. You can restrict application access based on source IP allowlisting using a new UI scope, ensuring that only users within your configured IP ranges can load the application after login.

The UI scope follows the same configuration pattern as existing API and cloud endpoint scopes, so you can add UI restrictions with a single API call alongside your existing NAC setup.

Learn more here: https://docs.getmontecarlo.com/docs/network-access-control

The Operations Agent now includes a ** Monitoring Agent** that proactively identifies monitoring gaps across your warehouse. Ask it to help you get started, and it analyzes your warehouse metadata, query logs, and usage patterns to discover business use cases, rank them by criticality, and surface the golden tables that feed your dashboards, ML models, and downstream operations.

For each use case, the Monitoring Agent highlights your most critical unmonitored tables with full context including upstream source count, read frequency, downstream consumers, and blast radius. A gap ranking shows unmonitored golden tables per use case with gap percentages, so you know exactly where to focus first.

Once you pick a scope and notification audience, the agent generates a complete monitor YAML configuration. Preview it, choose draft or active, and deploy with one click.

Available in Preview.

SLO policies let you define Time to Acknowledge (TTA) and Time to Resolve (TTR) thresholds for alerts, scoped by priority and domain. Set the response time standards that matter to your organization and track compliance directly in Monte Carlo.

The Alerts table now includes an SLO Status column you can sort and filter to surface overdue alerts at a glance. Alert detail pages display a countdown or breach timer showing exactly how much time remains or how far past your SLO an alert has gone. Optionally, configure re-notifications to alert the original audience when a threshold is breached.

Available to all accounts as an opt-in feature in public preview.

Learn more here: https://docs.getmontecarlo.com/docs/service-level-objectives-slos

The monitor creation modal now includes an “Ask AI” feature, allowing you to describe your monitoring needs in plain language. The Operations Agent then provides guided support to help configure your monitor setup.

To get started quickly, you can use example prompts - or enter more complex requests - to receive guidance and successfully create the monitors you need.