Three new skills in the MC Agent Toolkit help your coding agent tackle warehouse optimization and agent monitoring.

Cost Savings identifies wasteful assets and helps clean your warehouse of stale and unneeded tables. Performance Diagnosis surfaces your worst-performing jobs and provides guidance on improving them. Agent Monitoring explores your agents and sets up monitors across all four supported types.

For best results, connect a database connector alongside the MC Agent Toolkit plugin (v1.4.0 or later).

Three new skills in the MC Agent Toolkit bring the full alert lifecycle into your coding agent.

Automated Triage fetches recent alerts, scores each one by confidence and impact, runs deep troubleshooting on high-signal alerts, and recommends actions. Start from a built-in example workflow or customize to match how your team responds.

Root Cause Analysis systematically investigates data incidents across freshness, volume, schema, field metrics, and ETL failures. It walks the lineage chain upstream, checks ETL jobs across Airflow, dbt, and Databricks, detects query changes, and profiles actual data when a database connector is available.

Remediation picks up where investigation ends. It discovers available tools, proposes a fix with risk assessment and rollback plan, executes with safety rails, and documents everything on the alert. All three skills compose naturally: triage surfaces alerts, root cause analysis investigates them, and remediation fixes them.

The Troubleshooting Agent now investigates job failures as a first-class incident type — in addition to the freshness, volume, and schema incidents it already handles.

What's new:

• Azure Data Factory pipeline failures — when an ADF pipeline failure causes a downstream data incident, the agent now identifies the exact failing pipeline in its root cause analysis, rather than flagging a pipeline-related issue
• Databricks Workflow failures are also supported
• Job runtime context across all incident types — even when an incident isn't a job failure itself, the agent can now correlate it with a long-running or failed job upstream (e.g. a freshness anomaly caused by a slow ADF or Databricks job)

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