io.github.enessari/metabase-ai-assistant

NPM · METABASE-AI-ASSISTANT · SCANNED AUG 3

MCP Server for Metabase - 111 tools for SQL generation, dashboards & PostgreSQL

Available components

+10 this week 34 34 Trust /100

Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security84

No malware found by supply-chain analysis.Pass
Only part of the dependency tree could be resolved (250 of 289), so this covers what we could see, not the whole tree.Partial
No install/post-install scripts declared.Pass
Only part of the dependency tree could be resolved (250 of 289), so this covers what we could see, not the whole tree. View diagnostics → Partial

Provenance & Transparency45

Source repository is publicly reachable at the declared URL. View diagnostics → Pass
Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
Clear OSI-approved license (Apache-2.0).Pass
Actively maintained (last published 172 days ago).Pass
Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail

Schema Quality & AI Usability0

Schema quality not yet verified: our sandbox run of this package did not complete, so we have no schema to assess.Unverified

Stability & Change Management0

Stability not yet verified: our sandbox run of this package did not complete, so we have no schema to compare.Unverified

Tool Coverage0

Tool coverage not yet verified: our sandbox run of this package did not complete, so we have no tool definitions to assess.Unverified

Capabilities0

Protocol version not yet verified: our sandbox run of this package did not complete, so we never saw its MCP handshake.Unverified

Unverified: 4 categories

Categories scored 0 because our sandbox run of this package has not given us the schema these checks need to read. That is a gap on our side rather than a finding about the package, and we only credit what we can confirm, so the score stands at 0 until the capture succeeds. We are working through the fleet, so this normally clears without any action from you. How we score packages →

Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · metabase-ai-assistant

Claude Codex opencode OpenClaw Hermes Other

# add to Claude Code

claude mcp add enessari-metabase-ai-assistant -- npx -y metabase-ai-assistant

# add to Codex CLI

codex mcp add enessari-metabase-ai-assistant -- npx -y metabase-ai-assistant

// opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "enessari-metabase-ai-assistant": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "metabase-ai-assistant"
      ],
      "enabled": true
    }
  }
}

# add to OpenClaw

openclaw mcp add enessari-metabase-ai-assistant --command npx --arg -y --arg metabase-ai-assistant

# ~/.hermes/config.yaml

mcp_servers:
  enessari-metabase-ai-assistant:
    command: "npx"
    args: ["-y", "metabase-ai-assistant"]

// mcp.json

{
  "mcpServers": {
    "enessari-metabase-ai-assistant": {
      "command": "npx",
      "args": [
        "-y",
        "metabase-ai-assistant"
      ]
    }
  }
}

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

2 Aug 26 +29
- Provenance: unverified → fail ▼ security
- Install scripts: unverified → pass ▲ security
- Known CVEs: unverified → partial ▲ security
- Malware scan: unverified → pass ▲ security
- Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
- Security disclosure: fail → unverified ▼ functional
- Dependency health: unverified → partial ▲ functional
- Maintenance: unverified → pass ▲ functional
- License: unverified → pass ▲ functional
- Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. functional
- Capabilities: Protocol version not yet verified: we do not have a sandbox capture of the MCP handshake this version of the package performs yet. functional
- Tool coverage: Tool coverage not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet. functional
- Licence: Apache-2.0 functional
31 Jul 26 −19
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
28 Jul 26 0
- Tool coverage: Tool coverage not yet verified: our sandbox run of this package did not complete, so we have no tool definitions to assess. functional
- Schema quality: Schema quality not yet verified: our sandbox run of this package did not complete, so we have no schema to assess. functional
27 Jul 26 24

First indexed and scored.

Show 3 earlier entries Hide earlier entries

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 250 packages

250 packages in the resolved dependency tree · 244 deprecated · 81 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 122 exposed · ~7,745 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens

activity_cleanup ~56

Clean up old activity logs to maintain performance and storage efficiency

Input Output Examples

Name	Type	Req	Description
dry_run	boolean	—	Preview what would be deleted without actually deleting
retention_days	number	—	Keep logs newer than this many days (default: 90)

No output schema declared.

No examples provided.

activity_database_usage ~39

Get database usage patterns and statistics showing which databases are most active

Input Output Examples

Name	Type	Req	Description
days	number	—	Number of days to analyze (default: 30)

No output schema declared.

No examples provided.

activity_error_analysis ~38

Analyze error patterns and common failure points to identify improvement opportunities

Input Output Examples

Name	Type	Req	Description
days	number	—	Number of days to analyze (default: 7)

No output schema declared.

No examples provided.

activity_log_init ~55

Initialize activity logging system for a database - creates log table and starts tracking operations

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID to initialize logging for
schema	string	—	Schema name for log table (default: public)

No output schema declared.

No examples provided.

activity_operation_stats ~36

Analyze operation statistics and patterns over specified time period

Input Output Examples

Name	Type	Req	Description
days	number	—	Number of days to analyze (default: 7)

No output schema declared.

No examples provided.

activity_performance_insights ~38

Get performance insights showing slow operations and optimization opportunities

Input Output Examples

Name	Type	Req	Description
days	number	—	Number of days to analyze (default: 7)

No output schema declared.

No examples provided.

activity_session_summary ~40

Get comprehensive summary of current or specified session activities and performance

Input Output Examples

Name	Type	Req	Description
session_id	string	—	Session ID to analyze (optional, defaults to current session)

No output schema declared.

No examples provided.

activity_timeline ~55

Get chronological timeline of recent activities for debugging and monitoring

Input Output Examples

Name	Type	Req	Description
days	number	—	Number of days to show (default: 7)
limit	number	—	Maximum number of activities to return (default: 100)

No output schema declared.

No examples provided.

ai_relationships_suggest ~68

AI-powered virtual relationship discovery using naming patterns and data analysis - finds implicit connections between tables

Input Output Examples

Name	Type	Req	Description
confidence_threshold	number	—	Minimum confidence level (0.0-1.0)
database_id	number	yes	Database ID
schema_name	string	yes	Schema name

No output schema declared.

No examples provided.

ai_sql_explain ~40

Break down complex SQL queries into plain English - explains joins, aggregations, and business logic

Input Output Examples

Name	Type	Req	Description
sql	string	yes	SQL query to explain

No output schema declared.

No examples provided.

ai_sql_generate ~54

Convert natural language requests into SQL queries - understands business context and table relationships

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID to generate query for
description	string	yes	Natural language description of what you want to query

No output schema declared.

No examples provided.

ai_sql_optimize ~39

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

Input Output Examples

Name	Type	Req	Description
sql	string	yes	SQL query to optimize

No output schema declared.

No examples provided.

db_ai_drop ~101

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

Input Output Examples

Name	Type	Req	Description
approved	boolean	—	Set to true to confirm deletion
database_id	number	yes	Database ID
dry_run	boolean	—	Set to true to preview without executing
object_name	string	yes	Object name to drop (must have claude_ai_ prefix)
object_type	string	yes	Type of object to drop

No output schema declared.

No examples provided.

db_ai_list ~38

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

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID to list objects from

No output schema declared.

No examples provided.

db_connection_info ~36

Get database connection information from Metabase (requires admin permissions)

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID to get connection info for

No output schema declared.

No examples provided.

db_index_create ~128

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

Input Output Examples

Name	Type	Req	Description
approved	boolean	—	Set to true to confirm execution
columns	array	yes	Array of column names or single column name
database_id	number	yes	Database ID to create index in
dry_run	boolean	—	Set to true to preview without executing
index_name	string	yes	Index name (claude_ai_ prefix will be added automatically)
table_name	string	yes	Table name to create index on
unique	boolean	—	Whether to create unique index

No output schema declared.

No examples provided.

db_index_usage ~63

Analyze index usage statistics - find unused or rarely used indexes

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID
min_size_mb	number	—	Minimum index size in MB to include
schema_name	string	—	Schema name to analyze (default: public)

No output schema declared.

No examples provided.

db_list ~23

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

Input Output Examples

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

db_matview_create ~125

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

Input Output Examples

Name	Type	Req	Description
approved	boolean	—	Set to true to confirm execution
database_id	number	yes	Database ID to create materialized view in
dry_run	boolean	—	Set to true to preview without executing
schema	string	—	Target schema name (optional, uses database default if not specified)
select_sql	string	yes	SELECT statement for the materialized view
view_name	string	yes	Materialized view name (claude_ai_ prefix will be added)

No output schema declared.

No examples provided.

db_query_explain ~89

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

Input Output Examples

Name	Type	Req	Description
analyze	boolean	—	Actually run the query to get real execution times
database_id	number	yes	Database ID
format	string	—	Output format for the plan
sql	string	yes	SQL query to analyze
verbose	boolean	—	Include additional details in the plan

No output schema declared.

No examples provided.

db_relationships_detect ~66

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

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID
schema_name	string	yes	Schema name to analyze
table_names	array	—	Specific tables to analyze (optional, analyzes all if not provided)

No output schema declared.

No examples provided.

db_schema_analyze ~99

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

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID
include_columns	boolean	—	Include detailed column information
limit	number	—	Maximum number of tables to analyze (default: 10)
schema_name	string	yes	Schema name to explore
timeout_seconds	number	—	Maximum execution time in seconds (default: 30)

No output schema declared.

No examples provided.

db_schema_explore ~67

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

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID
limit	number	—	Maximum number of tables to return (default: 20)
schema_name	string	yes	Schema name to explore

No output schema declared.

No examples provided.

db_schemas ~37

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

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID

No output schema declared.

No examples provided.

db_sync_schema ~28

Trigger schema sync for a database

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID to sync

No output schema declared.

No examples provided.

db_table_create ~117

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

Input Output Examples

Name	Type	Req	Description
approved	boolean	—	Set to true to confirm execution
columns	array	yes	Array of column definitions
database_id	number	yes	Database ID to create table in
dry_run	boolean	—	Set to true to preview without executing
schema	string	—	Target schema name (optional, uses database default if not specified)
table_name	string	yes	Table name (claude_ai_ prefix will be added automatically)

No output schema declared.

No examples provided.

db_table_ddl ~47

Get the DDL (CREATE statement) for a table

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID
table_name	string	yes	Table name to get DDL for

No output schema declared.

No examples provided.

db_table_stats ~65

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

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID
schema_name	string	—	Schema name (default: public)
table_name	string	yes	Table name to get stats for

No output schema declared.

No examples provided.

db_tables ~35

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

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID

No output schema declared.

No examples provided.

db_test_speed ~39

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

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID to test

No output schema declared.

No examples provided.

db_test_speed ~31

Quick test to check database connection and response time

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID to test

No output schema declared.

No examples provided.

db_vacuum_analyze ~106

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

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID
dry_run	boolean	—	Preview command without executing
schema_name	string	—	Schema name (default: public)
table_name	string	—	Table name to vacuum/analyze (optional, all tables if not specified)
vacuum_type	string	—	Type of maintenance operation

No output schema declared.

No examples provided.

db_view_create ~119

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

Input Output Examples

Name	Type	Req	Description
approved	boolean	—	Set to true to confirm execution
database_id	number	yes	Database ID to create view in
dry_run	boolean	—	Set to true to preview without executing
schema	string	—	Target schema name (optional, uses database default if not specified)
select_sql	string	yes	SELECT statement for the view
view_name	string	yes	View name (claude_ai_ prefix will be added automatically)

No output schema declared.

No examples provided.

db_view_ddl ~47

Get the DDL (CREATE statement) for a view

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID
view_name	string	yes	View name to get DDL for

No output schema declared.

No examples provided.

definition_get_metric ~44

Get metric definition with calculation formula and business context

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID to search in
metric_name	string	yes	Metric name to lookup

No output schema declared.

No examples provided.

definition_get_template ~57

Get dashboard or question template with layout and configuration

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID to search in
template_name	string	yes	Template name to lookup
template_type	string	yes	Type of template to retrieve

No output schema declared.

No examples provided.

definition_global_search ~66

Search across all definition tables with unified results

Input Output Examples

Name	Type	Req	Description
content_types	array	—	Filter by content types (business_terms, metrics, templates, etc.)
database_id	number	yes	Database ID to search in
search_term	string	yes	Term to search across all definitions

No output schema declared.

No examples provided.

definition_search_terms ~63

Search business terms and definitions with relevance ranking

Input Output Examples

Name	Type	Req	Description
category	string	—	Optional category filter (customer_metrics, revenue_metrics, etc.)
database_id	number	yes	Database ID to search in
search_term	string	yes	Term to search for in definitions

No output schema declared.

No examples provided.

definition_tables_init ~39

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

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID to create definition tables in

No output schema declared.

No examples provided.

mb_action_create ~111

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

Input Output Examples

Name	Type	Req	Description
database_id	number	—	Database ID for query actions
dataset_query	object	—	Query definition for query actions
description	string	—	Action description
model_id	number	yes	Model ID the action belongs to
name	string	yes	Action name
parameters	array	—	Action parameters
type	string	yes	Action type
visualization_settings	object	—	Form visualization settings

No output schema declared.

No examples provided.

mb_action_execute ~41

Execute a Metabase action with parameters

Input Output Examples

Name	Type	Req	Description
action_id	number	yes	Action ID to execute
parameters	object	yes	Parameter values for the action

No output schema declared.

No examples provided.

mb_action_list ~30

List all actions for a model

Input Output Examples

Name	Type	Req	Description
model_id	number	yes	Model ID to get actions for

No output schema declared.

No examples provided.

mb_alert_create ~88

Create an alert for a question that triggers on specified conditions

Input Output Examples

Name	Type	Req	Description
alert_above_goal	boolean	—	Alert when above goal (for goal condition)
alert_condition	string	—	Alert condition type
alert_first_only	boolean	—	Only alert on first occurrence
card_id	number	yes	Question/Card ID to create alert for
channels	array	—	Notification channels

No output schema declared.

No examples provided.

mb_alert_list ~33

List all alerts, optionally filtered by question

Input Output Examples

Name	Type	Req	Description
card_id	number	—	Filter alerts by question ID (optional)

No output schema declared.

No examples provided.

mb_auto_describe ~68

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

Input Output Examples

Name	Type	Req	Description
database_id	number	yes	Database ID to generate descriptions for
force_update	boolean	—	Update existing descriptions (default: false)
target_type	string	—	What to generate descriptions for

No output schema declared.

No examples provided.

mb_bookmark_create ~39

Bookmark an item for quick access

Input Output Examples

Name	Type	Req	Description
id	number	yes	Item ID to bookmark
type	string	yes	Item type to bookmark

No output schema declared.

No examples provided.

mb_bookmark_delete ~32

Remove a bookmark

Input Output Examples

Name	Type	Req	Description
id	number	yes	Item ID
type	string	yes	Item type

No output schema declared.

No examples provided.

mb_bookmark_list ~15

List all bookmarked items

Input Output Examples

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

mb_cache_invalidate ~52

Invalidate cache for specific items or entire database

Input Output Examples

Name	Type	Req	Description
card_id	number	—	Specific card ID to invalidate
database_id	number	—	Database ID (optional, invalidates all if provided alone)

No output schema declared.

No examples provided.

mb_card_archive ~31

Archive a card/question (soft delete)

Input Output Examples

Name	Type	Req	Description
card_id	number	yes	Card/Question ID to archive

No output schema declared.

No examples provided.

On this page

Handy links

Scoring key

80+ high trust
60–79 medium
below 60 low

How we score

Score history · last 30 days

27 Jul 3 Aug