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 · SCANNED SEP 21

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

+1 this week 81 Trust /100
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 Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 91 of 274 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency48
  • 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 221 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 Management97
  • Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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
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
// .cursor/mcp.json
{
  "mcpServers": {
    "enessari-metabase-ai-assistant": {
      "command": "npx",
      "args": [
        "-y",
        "metabase-ai-assistant"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "enessari-metabase-ai-assistant": {
      "command": "npx",
      "args": [
        "-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"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "enessari-metabase-ai-assistant": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "metabase-ai-assistant"
      ]
    }
  }
}
# add to Vellum
assistant mcp add enessari-metabase-ai-assistant -t stdio -c npx -a -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.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 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.

  • 16 Sept 26 −1
    • CVE-2026-82562 no longer affects this package security
    • CVE-2026-82417 no longer affects this package security
    • Known CVEs: fail → pass security
    • Stability: pass → 0.80 functional
  • 15 Sept 26 0
    • Stability: 0.97 → pass security
  • 14 Sept 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.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 −2
    • Stability: pass → 0.83 functional
  • 9 Sept 26 0
    • Stability: 0.97 → pass security
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 Sept 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 →

Dependencies 274 packages
Packages resolved 274
Deprecated 1
Stale 90
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_question_create_parametric ~124

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

NameTypeReqDescription
collection_idnumberCollection ID to save question to (optional)
database_idnumberyesDatabase ID
descriptionstringQuestion description
namestringyesQuestion name
parametersarrayParameter definitions for the question
sqlstringyesSQL query with parameter placeholders (e.g., {{date_range}}, {{category_filter}})
visualizationstringChart type

No output schema declared.

No examples provided.

mb_questions ~39

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

NameTypeReqDescription
collection_idnumberFilter by collection ID (optional)

No output schema declared.

No examples provided.

mb_relationships_create ~63

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

NameTypeReqDescription
confirmedbooleanConfirm that relationships have been reviewed
database_idnumberyesDatabase ID
relationshipsarrayyesArray of confirmed relationships to create

No output schema declared.

No examples provided.

mb_search ~71

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

NameTypeReqDescription
collection_idnumberSearch within specific collection
limitnumberMaximum results to return
modelsarrayFilter by item types (default: all)
querystringyesSearch query text

No output schema declared.

No examples provided.

mb_segment_create ~64

Create a segment (reusable filter) for a table

NameTypeReqDescription
definitionobjectyesMBQL filter definition
descriptionstringSegment description
namestringyesSegment name
table_idnumberyesTable ID to create segment for

No output schema declared.

No examples provided.

mb_segment_list ~27

List all segments

NameTypeReqDescription
table_idnumberFilter by table ID (optional)

No output schema declared.

No examples provided.

mb_table_metadata ~68

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

NameTypeReqDescription
descriptionstringTable description
display_namestringHuman-readable display name
table_idnumberyesTable ID to get/update
visibility_typestringTable visibility type

No output schema declared.

No examples provided.

mb_user_create ~87

Create a new Metabase user

NameTypeReqDescription
emailstringyesUser email address (also used as login)
first_namestringyesUser first name
group_idsarrayArray of permission group IDs to assign
last_namestringyesUser last name
passwordstringInitial password (optional, will send invite email if not provided)

No output schema declared.

No examples provided.

mb_user_disable ~30

Disable (deactivate) a user account

NameTypeReqDescription
user_idnumberyesUser ID to disable

No output schema declared.

No examples provided.

mb_user_get ~29

Get detailed information about a specific user

NameTypeReqDescription
user_idnumberyesUser ID to retrieve

No output schema declared.

No examples provided.

mb_user_list ~44

List all Metabase users with filtering options

NameTypeReqDescription
group_idnumberFilter by permission group ID (optional)
statusstringFilter by user status

No output schema declared.

No examples provided.

mb_user_update ~83

Update an existing user

NameTypeReqDescription
emailstringNew email address
first_namestringNew first name
group_idsarrayNew permission group IDs
is_superuserbooleanSet superuser status
last_namestringNew last name
user_idnumberyesUser ID to update

No output schema declared.

No examples provided.

mb_visualization_recommend ~64

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

NameTypeReqDescription
data_sampleobjectSample data to analyze (optional if question_id provided)
purposestringPurpose of the visualization
question_idnumberyesQuestion ID to analyze

No output schema declared.

No examples provided.

mb_visualization_settings ~63

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

NameTypeReqDescription
displaystringChart display type
question_idnumberyesQuestion ID to get/update visualization for
settingsobjectVisualization settings object

No output schema declared.

No examples provided.

parametric_dashboard_create ~98

Create dashboard with parametric questions and shared filters

NameTypeReqDescription
collection_idnumberCollection ID to save dashboard to
database_idnumberyesDatabase ID to create dashboard in
descriptionstringDashboard description
filtersobjectDashboard-level filters
layoutarrayLayout configuration for questions
namestringyesDashboard name
questionsarrayyesArray of question configurations

No output schema declared.

No examples provided.

parametric_question_create ~115

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

NameTypeReqDescription
collection_idnumberCollection ID to save question to
database_idnumberyesDatabase ID to create question in
descriptionstringQuestion description
namestringyesQuestion name
parametersobjectyesParameter definitions with types and defaults
question_typestring
sql_templatestringyesSQL template with parameter placeholders (e.g., {{date_range}}, {{search_term}})

No output schema declared.

No examples provided.

parametric_template_preset ~84

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

NameTypeReqDescription
collection_idnumberCollection ID to save question to
configobjectyesConfiguration for the preset template
database_idnumberyesDatabase ID to create question in
preset_typestringyesPreset template type

No output schema declared.

No examples provided.

sql_execute ~52

Run SQL queries against database - supports SELECT, DDL with security controls, returns formatted results

NameTypeReqDescription
database_idnumberyesDatabase ID to execute query against
sqlstringyesSQL query to execute

No output schema declared.

No examples provided.

web_explore_metabase_docs ~91

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

NameTypeReqDescription
depthnumberCrawling depth (1=main sections, 2=subsections, 3=deep crawl)
focus_areasarraySpecific areas to focus on during exploration
include_examplesbooleanInclude code examples and API samples

No output schema declared.

No examples provided.

web_fetch_metabase_docs ~69

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

NameTypeReqDescription
search_termsstringSpecific terms to search in documentation
topicstringyesDocumentation topic to fetch (e.g., "dashboard-api", "questions", "parameters", "charts")

No output schema declared.

No examples provided.

web_metabase_api_reference ~66

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

NameTypeReqDescription
auth_infobooleanInclude authentication and permission details
endpoint_categorystringAPI category to explore
include_examplesbooleanInclude request/response examples

No output schema declared.

No examples provided.

web_search_metabase_docs ~85

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

NameTypeReqDescription
doc_typestringType of documentation to prioritize
max_resultsnumberMaximum number of relevant pages to return
querystringyesSearch query (e.g., "dashboard API create card", "parameter filters", "embedding iframe")

No output schema declared.

No examples provided.

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 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 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 September 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.