Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.enessari/metabase-ai-assistant

NPM · METABASE-AI-ASSISTANT

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

0 this week 76 Trust /100

Last scanned (23 hours ago)

Scores higher than 53% of npm servers

Category Data and Analytics

Trust breakdown (7 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 → Why this is hard to score →

Supply Chain Security81
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 92 of 272 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency47
  • 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 282 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability68
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 7745 tokens (~63/item across 122 items; 122 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 10 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "sql_execute" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 122 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

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.

  • 21 Nov 26 0
    • Stability: 0.97 → pass security
  • 20 Nov 26 0
    • Stability: pass → 0.97 functional
  • 14 Nov 26 0
    • Stability: 0.97 → pass security
  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 8 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

  • 6 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

  • 4 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

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 21 Nov 2026 · Analysed npm/metabase-ai-assistant@3.2.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-mrhx-c7xc-m3w5 CVE-2023-54404 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 272 packages
Packages resolved 272
Deprecated 1
Stale 91
Tree resolution Complete

Background: SBOMs and build attestations, explained →

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. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
mb_card_clone ~76

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

NameTypeReqDescription
card_idnumberyesSource card ID
collection_idnumber–Destination collection ID
column_mappingsobject–Column name mappings from source to target table
target_table_idnumberyesNew target table ID

No output schema declared.

No examples provided.

mb_card_copy ~62

Copy a card/question to a new location

NameTypeReqDescription
card_idnumberyesSource card ID
collection_idnumber–Destination collection ID
new_namestring–Name for the copy (optional, defaults to "Copy of [original]")

No output schema declared.

No examples provided.

mb_card_data ~55

Execute a card/question and get the results in specified format

NameTypeReqDescription
card_idnumberyesCard/Question ID
formatstring–Output format
parametersobject–Optional parameters for parametric questions

No output schema declared.

No examples provided.

mb_card_delete ~30

Permanently delete a card/question

NameTypeReqDescription
card_idnumberyesCard/Question ID to delete

No output schema declared.

No examples provided.

mb_card_get ~30

Get detailed information about a specific card/question

NameTypeReqDescription
card_idnumberyesCard/Question ID

No output schema declared.

No examples provided.

mb_card_update ~77

Update an existing card/question

NameTypeReqDescription
card_idnumberyesCard/Question ID
collection_idnumber–Move to collection ID
descriptionstring–New description
displaystring–Chart type
namestring–New name
visualization_settingsobject–New visualization settings

No output schema declared.

No examples provided.

mb_collection_copy ~52

Copy an entire collection with all contents

NameTypeReqDescription
collection_idnumberyesSource collection ID
destination_idnumber–Destination parent collection ID
new_namestring–Name for the copy

No output schema declared.

No examples provided.

mb_collection_create ~68

Create a new collection in Metabase for organizing questions and dashboards

NameTypeReqDescription
colorstring–Collection color (hex code)
descriptionstring–Collection description
namestringyesCollection name
parent_idnumber–Parent collection ID (null for root level)

No output schema declared.

No examples provided.

mb_collection_list ~48

List all collections with hierarchy and item counts

NameTypeReqDescription
include_itemsboolean–Include items in each collection
parent_idnumber–Filter by parent collection ID (null for root)

No output schema declared.

No examples provided.

mb_collection_move ~64

Move questions, dashboards, or collections to a different collection

NameTypeReqDescription
item_idnumberyesID of the item to move
item_typestringyesType of item to move
target_collection_idnumberyesTarget collection ID (null for root)

No output schema declared.

No examples provided.

mb_collection_permissions_get ~35

Get permissions graph for a collection

NameTypeReqDescription
collection_idnumberyesCollection ID (use "root" for root collection)

No output schema declared.

No examples provided.

mb_collection_permissions_update ~48

Update permissions for a collection

NameTypeReqDescription
collection_idnumberyesCollection ID
group_idnumberyesPermission group ID
permissionstringyesPermission level to set

No output schema declared.

No examples provided.

mb_dashboard_add_card ~83

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

NameTypeReqDescription
dashboard_idnumberyesDashboard ID to add card to
parameter_mappingsarray–Connect dashboard filters to question parameters
positionobject–Card position and size on dashboard grid
question_idnumberyesQuestion ID to add as card

No output schema declared.

No examples provided.

mb_dashboard_add_filter ~112

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

NameTypeReqDescription
dashboard_idnumberyesDashboard ID to add filter to
default_value––Default filter value (optional)
field_idnumber–Field ID to filter on (optional for some filter types)
namestringyesFilter display name
positionobject–Filter position in dashboard header
requiredboolean–Whether filter is required
typestringyesFilter type and operator

No output schema declared.

No examples provided.

mb_dashboard_card_remove ~40

Remove a card from a dashboard

NameTypeReqDescription
card_idnumberyesDashboard card ID to remove
dashboard_idnumberyesDashboard ID

No output schema declared.

No examples provided.

mb_dashboard_card_update ~84

Update card position and size on a dashboard

NameTypeReqDescription
card_idnumberyesDashboard card ID
colnumber–New column position
dashboard_idnumberyesDashboard ID
rownumber–New row position
size_xnumber–Width in grid units
size_ynumber–Height in grid units

No output schema declared.

No examples provided.

mb_dashboard_copy ~74

Copy a dashboard with all its cards

NameTypeReqDescription
collection_idnumber–Destination collection ID
dashboard_idnumberyesSource dashboard ID
deep_copyboolean–If true, also copies all cards. If false, links to existing cards.
new_namestring–Name for the copy

No output schema declared.

No examples provided.

mb_dashboard_create ~81

Create a new dashboard in Metabase with layout options

NameTypeReqDescription
collection_idnumber–Collection ID to save dashboard to (optional)
descriptionstringyesDashboard description
namestringyesDashboard name
templatestring–Dashboard template type
widthnumber–Dashboard width in grid units (default: 12)

No output schema declared.

No examples provided.

mb_dashboard_delete ~25

Delete a dashboard

NameTypeReqDescription
dashboard_idnumberyesDashboard ID to delete

No output schema declared.

No examples provided.

mb_dashboard_get ~26

Get detailed information about a dashboard

NameTypeReqDescription
dashboard_idnumberyesDashboard ID

No output schema declared.

No examples provided.

mb_dashboard_layout_optimize ~76

Automatically optimize dashboard layout for better visual hierarchy and user experience

NameTypeReqDescription
dashboard_idnumberyesDashboard ID to optimize
grid_widthnumber–Dashboard grid width (default: 12)
layout_stylestring–Layout optimization style
preserve_orderboolean–Keep existing card order when optimizing

No output schema declared.

No examples provided.

mb_dashboard_template_executive ~127

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

NameTypeReqDescription
business_domainstring–Business domain (e.g., ecommerce, saas, retail, finance)
collection_idnumber–Collection ID to save dashboard to (optional)
database_idnumberyesDatabase ID to analyze and create dashboard for
namestringyesDashboard name
schema_namestring–Target schema name for analysis (optional)
time_periodstring–Default time period for metrics

No output schema declared.

No examples provided.

mb_dashboard_update ~62

Update dashboard properties

NameTypeReqDescription
collection_idnumber–Move to collection
dashboard_idnumberyesDashboard ID
descriptionstring–New description
enable_embeddingboolean–Enable embedding
namestring–New name

No output schema declared.

No examples provided.

mb_dashboards ~13

List existing dashboards

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

mb_embed_settings ~21

Get embedding settings and enabled features for the Metabase instance

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

mb_embed_url_generate ~115

Generate signed embedding URL for a dashboard or question

NameTypeReqDescription
borderedboolean–Show border around embed
exp_minutesnumber–Token expiration in minutes
paramsobject–Locked parameter values for the embedding
previewboolean–Include preview-mode frame styles
resource_idnumberyesID of the dashboard or question
resource_typestringyesType of resource to embed
themestring–Embed theme
titledboolean–Show title in embed

No output schema declared.

No examples provided.

mb_field_metadata ~97

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

NameTypeReqDescription
descriptionstring–Field description
display_namestring–Human-readable display name
field_idnumberyesField ID to get/update
has_field_valuesstring–How to show field values in filters
semantic_typestring–Semantic type for the field
visibility_typestring–Field visibility

No output schema declared.

No examples provided.

mb_field_values ~35

Get distinct values for a field (for filter dropdowns)

NameTypeReqDescription
field_idnumberyesField ID to get values for

No output schema declared.

No examples provided.

mb_meta_auto_cleanup ~191

🧹 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.

NameTypeReqDescription
approvedboolean–🔒 SAFETY: Requires explicit approval (default: false). Set true to execute
broken_questionsboolean–Include questions with 100% error rate (default: true)
dry_runboolean–🔒 SAFETY: Dry-run mode (default: true). Set false to execute
empty_collectionsboolean–Include empty collections (default: true)
orphaned_cardsboolean–Include orphaned cards (not in dashboards) (default: true)
unused_daysnumber–Days without usage to consider content unused (default: 180)

No output schema declared.

No examples provided.

mb_meta_compare_environments ~59

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

NameTypeReqDescription
target_workspaceobjectyesWorkspace export from target environment

No output schema declared.

No examples provided.

mb_meta_content_usage ~100

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

NameTypeReqDescription
daysnumber–Number of days to analyze (default: 30)
limitnumber–Number of top items to return (default: 20)
unused_threshold_daysnumber–Days without usage to consider content "unused" (default: 90)

No output schema declared.

No examples provided.

mb_meta_dashboard_complexity ~36

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

mb_meta_database_usage ~63

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

NameTypeReqDescription
database_idnumber–Optional: analyze specific database tables
daysnumber–Number of days to analyze (default: 30)

No output schema declared.

No examples provided.

mb_meta_error_patterns ~96

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.

NameTypeReqDescription
daysnumber–Number of days to analyze (default: 30)
include_recurring_questionsboolean–Include questions with recurring errors (default: true)
include_timelineboolean–Include temporal error analysis (default: true)

No output schema declared.

No examples provided.

mb_meta_export_workspace ~120

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

NameTypeReqDescription
archivedboolean–Include archived items (default: false)
collection_idsarray–Optional: Export specific collections only (array of IDs)
include_collectionsboolean–Include collections (default: true)
include_dashboardsboolean–Include dashboards (default: true)
include_questionsboolean–Include questions (default: true)

No output schema declared.

No examples provided.

mb_meta_impact_analysis ~82

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.

NameTypeReqDescription
database_idnumberyesDatabase ID
schema_namestring–Schema name (optional)
table_namestringyesTable name to analyze for removal impact

No output schema declared.

No examples provided.

mb_meta_import_preview ~58

🔍 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.

NameTypeReqDescription
workspaceobjectyesWorkspace data from export_workspace

No output schema declared.

No examples provided.

mb_meta_info ~37

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

mb_meta_optimization_recommendations ~108

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

NameTypeReqDescription
database_idnumberyesDatabase ID to analyze
daysnumber–Number of days to analyze (default: 30)
include_cache_recommendationsboolean–Include cache optimization suggestions (default: true)
include_matview_candidatesboolean–Include materialized view recommendations (default: true)

No output schema declared.

No examples provided.

mb_meta_query_performance ~100

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.

NameTypeReqDescription
daysnumber–Number of days to analyze (default: 7)
include_slow_queriesboolean–Include detailed slow query analysis (default: true)
slow_threshold_msnumber–Threshold for slow queries in milliseconds (default: 10000)

No output schema declared.

No examples provided.

mb_meta_table_dependencies ~85

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.

NameTypeReqDescription
database_idnumberyesDatabase ID containing the table
schema_namestring–Schema name (optional, recommended for disambiguation)
table_namestringyesName of the table to analyze

No output schema declared.

No examples provided.

mb_meta_user_activity ~99

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.

NameTypeReqDescription
daysnumber–Number of days to analyze (default: 30)
inactive_threshold_daysnumber–Days without activity to consider user "inactive" (default: 90)
include_login_historyboolean–Include login timeline data (default: true)

No output schema declared.

No examples provided.

mb_metric_create ~83

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

NameTypeReqDescription
aggregationobjectyesMetric aggregation definition
descriptionstringyesMetric description and business context
filtersarray–Optional filters to apply to metric calculation
namestringyesMetric name
table_idnumberyesBase table ID for the metric

No output schema declared.

No examples provided.

mb_permission_group_add_user ~42

Add a user to a permission group

NameTypeReqDescription
group_idnumberyesPermission group ID
user_idnumberyesUser ID to add

No output schema declared.

No examples provided.

mb_permission_group_create ~28

Create a new permission group

NameTypeReqDescription
namestringyesName of the permission group

No output schema declared.

No examples provided.

mb_permission_group_delete ~27

Delete a permission group

NameTypeReqDescription
group_idnumberyesGroup ID to delete

No output schema declared.

No examples provided.

mb_permission_group_list ~18

List all permission groups in Metabase

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

mb_permission_group_remove_user ~42

Remove a user from a permission group

NameTypeReqDescription
group_idnumberyesPermission group ID
user_idnumberyesUser ID to remove

No output schema declared.

No examples provided.

mb_pulse_create ~87

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

NameTypeReqDescription
cardsarrayyesCards to include in the pulse
channelsarrayyesDelivery channels (email/slack)
collection_idnumber–Collection to save pulse in
namestringyesPulse name
skip_if_emptyboolean–Skip sending if no results

No output schema declared.

No examples provided.

mb_question_create ~79

Create new question/chart

NameTypeReqDescription
collection_idnumber–Collection ID to save the question to (optional)
database_idnumberyesDatabase ID to query
descriptionstringyesDescription of what the question shows
namestringyesName for the question
sqlstringyesSQL query for the question

No output schema declared.

No examples provided.

Install

How do I install the io.github.enessari/metabase-ai-assistant MCP server?

io.github.enessari/metabase-ai-assistant runs locally as an npm package, launched with npx -y metabase-ai-assistant. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · metabase-ai-assistant

# add to Claude Code
claude mcp add enessari-metabase-ai-assistant -- npx -y metabase-ai-assistant
Common questions

What is the io.github.enessari/metabase-ai-assistant MCP server?

io.github.enessari/metabase-ai-assistant is an MCP server listed in the public MCP registry as io.github.enessari/metabase-ai-assistant. MCP Server for Metabase - 111 tools for SQL generation, dashboards & PostgreSQL. This page covers its npm package (metabase-ai-assistant).

Is the io.github.enessari/metabase-ai-assistant MCP server safe to use?

io.github.enessari/metabase-ai-assistant scores 76 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.enessari/metabase-ai-assistant MCP server expose?

io.github.enessari/metabase-ai-assistant exposes 122 tools: db_list, db_test_speed, db_schemas, db_tables, sql_execute, and 117 more. Their descriptions and schemas cost roughly 7,745 tokens of context every time the server is loaded.

Is the io.github.enessari/metabase-ai-assistant MCP server still maintained?

io.github.enessari/metabase-ai-assistant is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.enessari/metabase-ai-assistant MCP server under?

io.github.enessari/metabase-ai-assistant declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the io.github.enessari/metabase-ai-assistant MCP server?

VerifyMCP ran 16 checks on io.github.enessari/metabase-ai-assistant, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.