Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_MODENoServer mode: read, write, or fullread
LOG_LEVELNoLogging: debug, info, warn, errorinfo
METABASE_URLYesYour Metabase instance URL
METABASE_API_KEYYesMetabase API key
METABASE_TIMEOUTNoRequest timeout (ms)30000
ANTHROPIC_API_KEYNoEnables NLQ and insight tools
METABASE_MAX_ROWSNoMax rows returned per query10000
RATE_LIMIT_REQUESTS_PER_MINUTENoRate limit threshold60

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_dashboardsA

List all dashboards in Metabase

get_dashboardA

Get dashboard details including its cards

list_cardsA

List questions/cards in Metabase. Returns up to 100 cards. Use search_content for discovery.

get_cardA

Get details of a specific question/card

execute_cardB

Execute an existing question/card and get results

list_databasesA

List all connected databases

get_database_schemaA

Get tables and columns for a database

execute_queryB

Execute a SQL query (SELECT statements only)

search_contentA

Search across Metabase content (dashboards, cards, collections)

get_collectionsA

List all collections

batch_executeA

Execute multiple read operations in a single call. Supports up to 20 operations run in parallel. Supported tools: get_dashboard, get_card, execute_card, get_database_schema, execute_query, search_content, list_dashboards, list_databases, list_cards.

run_workflowA

Execute a multi-step workflow pipeline in a single call. Steps run sequentially and can reference previous step results using "$stepName.path" syntax. Example: search for dashboards, then get details of the first result, then execute its cards — all in one call. Max 10 steps.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/1luvc0d3/metabase-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server