Metabase AI Assistant

Analyze and improve SQL query performance - suggests indexes, query restructuring, and execution optimizations

Safely remove AI-created database objects - only works on objects with claude_ai_ prefix for security

List all database objects created by AI (with claude_ai_ prefix)

Get database connection information from Metabase (requires admin permissions)

Create database index for query performance - improves search and join operations on specified columns

Analyze index usage statistics - find unused or rarely used indexes

Get list of all databases in Metabase instance with IDs and connection types

Create a new materialized view directly in the database (PostgreSQL only)

Get execution plan for a SQL query - shows how PostgreSQL will execute the query

Detect existing foreign key relationships between tables - finds explicitly defined database constraints

Deep schema analysis with column details, keys, constraints - requires direct DB connection for comprehensive insights

Fast schema exploration with table counts and basic info - lightweight method for discovering data structure

Get all schema names in specified database - useful for data exploration and finding business data locations

Trigger schema sync for a database

Create new table directly in database with security controls - requires schema selection and approval

Get the DDL (CREATE statement) for a table

Get comprehensive table profile: row count, column types, distinct values, sample data. Auto-detects dimension/reference tables (dim_, ref_, lookup_ prefix). Ideal for understanding lookup tables before writing queries.

Get table statistics including row count, size, dead tuples, last vacuum/analyze times

Get comprehensive table list across all schemas with field counts - provides overview of data structure

Check database response time and performance - run this before heavy operations to determine optimal timeout settings

Run VACUUM and ANALYZE on PostgreSQL tables to optimize storage and update statistics (PostgreSQL only)

Create a new view directly in the database (with claude_ai_ prefix)

Get the DDL (CREATE statement) for a view

🎨 [LIGHTDASH CODE-AS-BI DASHBOARD BUILDER] Build complete, publication-ready Metabase dashboards directly from dbt project YAML definitions (exposures.yml, semantic metrics, meta.metabase, and meta.lightdash). Constructs native Metabase Questions and Metabase Model cards (v50+), computes collision-free 24-column grid coordinates with executive visual hierarchy, and binds global interactive filter parameters in a single atomic operation.

🔁 [REVERSE LINEAGE] Scan all Metabase Dashboards and Questions, extract underlying dbt model dependencies (fct_, dim_, stg_), and generate models/exposures/_metabase__exposures.yml for dbt Docs and Lineage DAG.

ℹ️ [dbt ARCHITECTURE] Inspect dbt project models, lineage, and architectural tiers (marts/facts, marts/dims, intermediate, staging) from manifest.json.

🔗 [dbt LINEAGE & MULTI-HOP JOINS] Build model dependency DAGs and resolve multi-hop semantic join paths (e.g. fct_orders -> dim_customers -> dim_regions) using dbt schema relationship tests, foreign keys, and MetricFlow entities. Generates validated ANSI SQL joins with confidence scoring.

📊 [dbt SOURCE RESOLUTION] Prioritize the most trustworthy and aggregated dbt models (Gold Marts fct_/dim_ > Silver int_ > Bronze stg_) for a given question or intent.

🔍 [dbt DEEP SCANNER] Recursively scan dbt project repositories (models, sources, exposures, seeds, macros, schema.yml, docs/*.md, manifest.json, and catalog.json). Extracts all architectural tiers (marts, intermediate, staging), column schemas, resolved doc blocks, catalog profiling stats, MetricFlow semantic layer definitions, and test relationships.

🌉 [OMNI.CO CONTROLLED SEMANTIC-TO-YAML EXPORTER] Bridge Metabase analytics back to dbt by exporting approved (ACTIVE) business rules, metric definitions, and filter expressions from SemanticMemory into syntactically valid dbt schema.yml, semantic_models.yml, and metrics.yml code blocks. Preserves complete audit provenance, stakeholder sign-offs, and soft-deprecation audit trails with zero destructive mutation.

⚡ [CUBE.JS PRE-AGGREGATION & ROLLUP ADVISOR] Formulate database-specific Pre-Aggregation and Rollup Materialized View DDL recommendations that accelerate repetitive analytical queries by 10x-100x. Supports additive, semi-additive, and non-additive metrics (HyperLogLog, sum/count decomposition) across PostgreSQL, BigQuery, Snowflake, ClickHouse, DuckDB, Redshift, and MySQL.

🤖 [dbt SMART QUESTION] Natural language question to verified Metabase Question Card. Injects active dbt semantic rules, auto-heals SQL, applies zero-leak PII masking, and saves with optimal executive visual chart type.

🔄 [dbt ➔ METABASE SYNC] Synchronize dbt table display names, column descriptions, semantic data types (type/Currency, type/CreationDate, type/Category, type/FK), and foreign keys directly into Metabase Data Model via API.

📊 [dbt METRICS ➔ METABASE] Ingest dbt MetricFlow and YAML metric definitions into official Metabase Metrics (/api/metric) so users can select verified business formulas in the Metabase query builder.

Get metric definition with calculation formula and business context

Get dashboard or question template with layout and configuration

Search across all definition tables with unified results

Search business terms and definitions with relevance ranking

Initialize definition lookup tables system for documentation, metrics, templates, and search

Create a Metabase Action for data modification (INSERT, UPDATE, DELETE)

Execute a Metabase action with parameters

List all actions for a model

Create an alert for a question that triggers on specified conditions

List all alerts, optionally filtered by question

Automatically generate AI-powered descriptions for databases, tables, and fields with timestamp signatures

Bookmark an item for quick access

Remove a bookmark

List all bookmarked items

Invalidate cache for specific items or entire database

Archive a card/question (soft delete)

Clone a card and retarget to a different table (for template cards)

Copy a card/question to a new location

Execute a card/question and get the results in specified format (JSON, CSV, XLSX)

Permanently delete a card/question

Get detailed information about a specific card/question

Update an existing card/question

Copy an entire collection with all contents

Create a new collection in Metabase for organizing questions and dashboards

List all collections with hierarchy and item counts

Move questions, dashboards, or collections to a different collection

Get permissions graph for a collection

Update permissions for a collection

Create a native SQL question with parameters (variables) directly via SQL. Essential for creating cards that accept dashboard filters.

Add a question card to a dashboard with specific positioning, sizing, and layout

Add multiple cards to a dashboard using direct SQL inserts. Bypasses API limits, ensures precise positioning, and prevents timeouts. Use this for complex layouts.

Add a filter to a dashboard for interactive data filtering across multiple cards

Remove a card from a dashboard

Update card position and size on a dashboard

Copy a dashboard with all its cards

Create a new dashboard in Metabase with layout options

Delete a dashboard

Get detailed information about a dashboard

Automatically optimize dashboard layout for better visual hierarchy and user experience

Create an executive dashboard with standard KPIs, metrics, and layout - auto-generates questions and arranges them professionally

Update dashboard properties

Batch update position and size of multiple dashboard cards via direct SQL. Guarantees layout application.

List existing dashboards

Get embedding settings and enabled features for the Metabase instance

Generate signed embedding URL for a dashboard or question

Get or update field metadata including display name, description, and semantic type

Get distinct values for a field (for filter dropdowns)

Link a dashboard filter to a card parameter via SQL. Updates parameter_mappings.

🧹 Auto-cleanup unused content with SAFETY CHECKS. ⚠️ DRY-RUN by default, requires approved:true for execution. Finds unused questions (180+ days), orphaned cards, empty collections, broken questions. Requires MB_METADATA_ENABLED=true.

🔄 Compare current environment with another (dev → staging → prod). Identifies drift, missing items, and differences. READ-ONLY operation. Requires MB_METADATA_ENABLED=true.

Analyze content usage patterns - find popular questions/dashboards, unused content, orphaned cards. Great for content cleanup and optimization. Requires MB_METADATA_ENABLED=true.

Analyze dashboard complexity - card counts, load times, performance issues. Identify dashboards that need optimization. Requires MB_METADATA_ENABLED=true.

Analyze database usage patterns - query counts, performance, errors by database and table. Requires MB_METADATA_ENABLED=true.

Analyze error patterns and categorize recurring errors - identify systemic issues, suggest resolutions, find questions with high error rates. Proactive error management. Requires MB_METADATA_ENABLED=true.

📤 Export workspace to JSON (questions, dashboards, collections). READ-ONLY operation - safe to execute. Perfect for backups and migrations. Requires MB_METADATA_ENABLED=true.

Analyze impact of removing a table - breaking changes, affected questions/dashboards, severity assessment, and recommendations. Critical for safe database migrations. Requires MB_METADATA_ENABLED=true.

🔍 Preview import impact WITHOUT making changes (dry-run). Analyzes conflicts, detects issues, provides recommendations. ALWAYS run this before actual import. Requires MB_METADATA_ENABLED=true.

Get overview of Metabase metadata database - active users, questions, dashboards, recent activity. Quick health check. Requires MB_METADATA_ENABLED=true.

Get comprehensive optimization recommendations - index suggestions, materialized view candidates, and cache optimization. Data-driven performance improvements. Requires MB_METADATA_ENABLED=true.

Get comprehensive query performance statistics from Metabase metadata - analyze execution times, cache hit rates, error rates, and identify slow queries. Requires MB_METADATA_ENABLED=true.

Analyze table dependencies - find all questions and dashboards that depend on a specific table. Essential for impact analysis before schema changes. Requires MB_METADATA_ENABLED=true.

Get user activity statistics - active users, inactive users, query patterns, login history. Useful for license optimization and user engagement analysis. Requires MB_METADATA_ENABLED=true.

Create a custom metric definition in Metabase for KPI tracking and business intelligence

Add a user to a permission group

Create a new permission group

Delete a permission group

List all permission groups in Metabase

Remove a user from a permission group

Create a scheduled report (pulse) that sends dashboards/questions on a schedule

Create new question/chart

Create a parametric question with filters, variables, and dynamic queries - supports date ranges, dropdowns, and field filters

Browse saved questions and charts in Metabase - filter by collection to find specific reports

Create virtual relationships in Metabase model - enables cross-table queries and improved dashboard capabilities

Search across all Metabase items (cards, dashboards, collections, tables)

Create a segment (reusable filter) for a table

List all segments

Get or update table metadata including display name, description, and visibility

Create a new Metabase user

Disable (deactivate) a user account

Get detailed information about a specific user

List all Metabase users with filtering options

Update an existing user

AI-powered visualization recommendation based on query results and data types

Get or update visualization settings for a question (chart type, colors, labels, etc.)

Deep search within SQL code, visualization settings, and descriptions across all questions and dashboards.

Analyze query performance and usage history from internal logs. Finds slow queries and top users.

Auto-detect the Metabase Internal Application Database ID from connected databases. Required for advanced metadata tools.

Find dependencies: Which dashboards and questions use a specific table or field? (Impact Analysis)

Create dashboard with parametric questions and shared filters

Create parametric question with date, text search, and category filters

Create parametric question from preset templates (date range analysis, category filter, text search, period comparison)

✅ [GOVERNANCE APPROVAL] Explicitly approve a proposed business rule to make it ACTIVE. Once active, it will be automatically injected into BI query generation.

🔒 [GOVERNANCE DEPRECATION] Safely soft-archive/comment-out an assistant-created rule with mandatory deprecation reason. NO HARD DELETION IS PERFORMED.

📚 [GOVERNANCE REGISTRY] List all business rules with their status (ACTIVE, PENDING_APPROVAL, DEPRECATED), stakeholder comments, and complete audit history.

⚠️ [GOVERNANCE PROPOSAL] Propose a new business term, metric calculation, or filter rule. ⚠️ RULE IS NOT ACTIVE UNTIL EXPLICITLY APPROVED via semantic_memory_approve.

Cancel a running async query. Also attempts to cancel on database server.

Run SQL queries against database - supports SELECT, DDL with security controls, returns formatted results. For long-running queries (>60s), use sql_submit instead.

Check status of an async query submitted via sql_submit. Returns results when complete.

Submit a long-running SQL query asynchronously. Returns immediately with job_id. Use sql_status to check progress. Ideal for queries that may take minutes.

Comprehensively explore Metabase documentation - crawls main docs and discovers all available sections, APIs, and guides

Fetch specific Metabase documentation page for API details, best practices, and feature information

Get comprehensive Metabase API reference with endpoints, parameters, examples, and response formats

Search across all Metabase documentation for specific topics, APIs, or solutions - uses intelligent content analysis