Skip to main content
Glama
MikelA92

Metabase MCP Server

by MikelA92

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
METABASE_URLNoYour Metabase instance URLhttps://data-metabase.swile.co
METABASE_API_KEYYesYour Metabase API key. Must be provided - no default value for security.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription
get_cardA

🔍 [SAFE] Get a Metabase card/question by ID, including its SQL query. Use this when you need to see the SQL behind a specific question or analyze how a card is built. Risk: None - read-only operation.

list_cardsA

📋 [SAFE] List Metabase cards/questions with optional filtering. Use this to discover available cards, find cards by type, or see all questions in the system. Can return large results (15k+ cards). Risk: None - read-only, but may be slow with many cards.

execute_card_queryA

▶️ [MODERATE RISK] Execute a saved card query and return results. Use this to get actual data from a card. May take time for complex queries. Risk: Moderate - executes queries that may be slow or resource-intensive. Does not modify data.

get_dashboardA

📊 [SAFE] Get a dashboard by ID including all its cards, layout, and parameters. Use this to understand dashboard structure or see all questions in a dashboard at once. Risk: None - read-only operation.

list_dashboardsA

📊 [SAFE] List all dashboards in Metabase. Use this to discover available dashboards or find dashboards by name. Risk: None - read-only operation.

get_databaseA

🗄️ [SAFE] Get database information by ID including engine type and connection details. Use this to understand which database a card connects to. Risk: None - read-only operation.

list_databasesA

🗄️ [SAFE] List all available databases. Use this to see what data sources are connected to Metabase. Risk: None - read-only operation.

get_database_metadataA

🔍 [SAFE] Get complete metadata for a database including ALL tables, columns, and field types. This is comprehensive and may return large amounts of data. Use this when you need to understand the full database schema. Risk: None - read-only, but returns large payloads.

list_database_tablesA

📑 [SAFE] List all tables in a specific database. Use this to see what tables are available before querying. Risk: None - read-only operation.

get_table_metadataA

🔍 [SAFE] Get detailed metadata for a specific table including all columns, data types, and foreign key relationships. Use this to understand table structure before writing queries. Risk: None - read-only operation.

list_collectionsA

📁 [SAFE] List all collections (folders) in Metabase. Collections organize cards and dashboards. Use this to understand the organizational structure. Risk: None - read-only operation.

get_collection_itemsA

📁 [SAFE] Get all items (cards, dashboards, models) in a specific collection. Use this to see what content is organized in a folder. Risk: None - read-only operation.

execute_native_queryA

⚠️ [MODERATE RISK] Execute an ad-hoc native SQL query directly against a database. Use this when you need to run custom SQL that doesn't exist as a saved card. Risk: Moderate - executes arbitrary SQL (read-only with API key, but can be slow or resource-intensive). Always validate SQL before executing.

get_fieldA

🔍 [SAFE] Get detailed information about a specific field/column including its type, description, and metadata. Use this to understand what a column contains. Risk: None - read-only operation.

get_field_valuesA

🔍 [SAFE] Get distinct values for a field (useful for understanding what values exist in a column). May return many values for high-cardinality fields. Risk: None - read-only, but may return large results.

list_segmentsA

🎯 [SAFE] List all segments (saved filters) in Metabase. Segments are reusable filters like "Active Users" or "Premium Customers". Risk: None - read-only operation.

list_metricsA

📊 [SAFE] List all metrics (saved aggregations) in Metabase. Metrics are reusable calculations like "Total Revenue" or "Average Order Value". Risk: None - read-only operation.

get_activityA

📜 [SAFE] Get recent activity feed showing views, edits, and other actions in Metabase. Use this to see what users are doing or what content is popular. Risk: None - read-only operation.

get_current_userA

👤 [SAFE] Get information about the currently authenticated user (you). Risk: None - read-only operation.

list_usersA

👥 [SAFE - REQUIRES ADMIN] List all Metabase users. Requires admin permissions. Use this to see who has access to Metabase. Risk: None - read-only, but may fail if not admin.

get_card_with_parametersA

🔗 [SAFE] Get a card with applied parameters from dashboard URL. Use this to extract card ID and parameters from Metabase dashboard URLs with filters. Risk: None - read-only operation.

execute_query_builder_cardA

⚙️ [MODERATE RISK] Execute a query-builder card with specific parameters. Use this to run query builder cards with custom filters and aggregations. Risk: Moderate - executes queries that may be slow or resource-intensive.

get_generated_sqlA

📝 [MODERATE RISK] Get the generated SQL for a query-builder card with parameters. Use this to see the actual SQL that Metabase generates from query builder parameters. Risk: Moderate - executes queries to generate SQL.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.9/5.0

Scored across 23 tools

Disambiguation3/5

Most tools have distinct purposes, but there is notable overlap among query execution tools (execute_card_query, execute_native_query, execute_query_builder_card) and metadata retrieval tools (get_database_metadata, get_table_metadata, get_field, get_field_values), which could cause confusion. Descriptions help differentiate them, but the boundaries are not entirely clear.

Naming Consistency5/5

Tool names follow a highly consistent verb_noun pattern throughout, with clear prefixes like 'execute_', 'get_', and 'list_'. There are no deviations in naming conventions, making the set predictable and easy to navigate.

Tool Count3/5

With 23 tools, the count feels heavy for a Metabase interface, as many tools are read-only metadata retrievals that could potentially be consolidated. While it covers many aspects, it borders on being overly granular for the domain.

Completeness4/5

The tool set provides comprehensive read-only coverage for querying, metadata, and listing resources in Metabase, with no major gaps for data retrieval. However, it lacks write operations (e.g., creating or updating cards, dashboards, or collections), which limits full lifecycle management.

Maintenance

ActivityInactive
ResponsivenessNo issues