Metabase
Metabase is an open-source business intelligence tool that lets you ask questions about your data and visualize answers as charts, graphs, and dashboards.
Verdict
Common use cases
- Pull weekly revenue metrics into standup notes
- Duplicate dashboards for regional team experiments
- Bookmark high-priority reports during sprint planning
- Clear stale cache after data pipeline updates
- Archive outdated actions when workflows change
Integration
- Vendor
- Metabase
- Category
- other
- Auth
- API_KEY
- Tools
- 50
- Composio slug
metabase
Tools
- Copy Dashboard
Tool to create a copy of an existing Metabase dashboard. Use when you need to duplicate a dashboard with optional customization of name, description, and collection placement. Supports both shallow copy (references same cards) and deep copy
- Create Bookmark
Tool to create a new bookmark for a Metabase item (card, dashboard, collection, or dataset). Use when the user wants to bookmark a specific item for quick access.
- Create Bookmark
Tool to create a new bookmark for a Metabase item (card, dashboard, collection, or dataset). Use when you need to bookmark a specific item for the authenticated user.
- Create Field Dimension
Tool to set the dimension for a field at the specified ID in Metabase. Use when you need to configure field remapping or display values for better data presentation.
- Delete Actiondestructive
Tool to delete a Metabase action by its ID. Use when you need to permanently remove an action from the system.
- Delete Actiondestructive
Tool to delete an Action from Metabase. Use when you need to permanently remove an action. This operation cannot be undone.
- Delete API Cachedestructive
Tool to delete/clear cached data in Metabase for specific entities. Use when you need to invalidate cache for a database, dashboard, question, or clear all cache (root).
- Delete Bookmarkdestructive
Tool to delete a bookmark from a Metabase item (card, dashboard, or collection). Use when you need to remove a bookmark from a specific item.
- Delete Bookmarkdestructive
Tool to delete a bookmark by model and ID. Use when you need to remove a bookmark assigned to the user making the request. The operation returns HTTP 204 No Content on successful deletion.
- Delete Carddestructive
Tool to hard delete a Metabase card. Use when you need to permanently remove a card from the system. For soft deletion, use PUT /api/card/:id instead.
- Delete Carddestructive
Tool to delete a Metabase card (question) by its ID. Use when you need to permanently remove a card. Note: This endpoint is deprecated - consider archiving cards instead.
- Delete Dashboarddestructive
Tool to hard delete a Metabase dashboard by its ID. Use when you need to permanently remove a dashboard. This will also remove any questions/models/segments/metrics that use this database. For soft delete, use the update dashboard action in
- Delete Dashboarddestructive
Tool to delete a Metabase dashboard by its ID. Use when you need to permanently remove a dashboard.
- Delete Field Dimensiondestructive
Tool to remove the dimension associated with a field at the specified ID. Use when you need to disassociate a dimension from a field in Metabase.
- Delete Glossary Entrydestructive
Tool to delete a glossary entry from Metabase. Use when you need to permanently remove a glossary entry by its ID.
- Delete Glossary Itemdestructive
Tool to delete a glossary item by ID. Use when you need to remove a glossary term from Metabase. The operation returns HTTP 204 No Content on successful deletion.
- Delete Model Indexdestructive
Tool to delete a ModelIndex by ID from Metabase. Use when you need to remove a model index from the system.
- Delete Model Indexdestructive
Tool to delete a Metabase model index by its ID. Use when you need to permanently remove a model index entry.
- Delete Timelinedestructive
Tool to delete a Metabase timeline and cascade delete all its associated events. Use when you need to permanently remove a timeline. Deletion is permanent and cannot be undone.
- Delete Timelinedestructive
Tool to delete a timeline by ID. Use when you need to permanently remove a timeline. Returns success status on completion.
- Delete Timeline Eventdestructive
Tool to delete a Metabase timeline event. Use when you need to permanently remove a timeline event from the system.
- Delete Timeline Eventdestructive
Tool to delete a timeline event by ID. Use when you need to permanently remove a specific timeline event from Metabase.
- Delete User Key-Valuedestructive
Tool to delete a user key-value pair from Metabase. Use when you need to remove a stored key-value entry within a specific namespace.
- Delete User Key-Value Pairdestructive
Tool to delete a user key-value pair by namespace and key. Use when you need to remove a specific key-value entry from a user's namespace.
- Delete User Subscriptionsdestructive
Tool to delete all Alert and DashboardSubscription subscriptions for a User. Use when you need to remove all subscriptions for a specific user and archive alerts/dashboards they created. This is an enterprise feature requiring admin privile
- Delete User Subscriptionsdestructive
Tool to delete all Alert and DashboardSubscription subscriptions for a User. Also archives all Alerts and DashboardSubscriptions created by the User. Requires premium token with :audit-app feature. Only allowed for admins or current user.
- Disable Database Model Persistence
Tool to disable model persistence for a Metabase database. Use when you need to turn off caching of model results. Returns success whether persistence was already disabled or not (idempotent operation).
- Discard Database Field Values
Tool to discard all saved field values for a specific database. Use when you need to clear cached field value data for all fields in a database. Requires superuser privileges.
- Discard Field Values
Tool to discard the FieldValues belonging to a Metabase field. Use when you need to clear cached field values. Only applies to fields that have FieldValues. If the Field's Database is set up to automatically sync FieldValues, they will be r
- Discard Table Field Values
Tool to discard the FieldValues belonging to the Fields in a Metabase Table. Use when you need to clear cached field values for all fields in a table. Only applies to fields that have FieldValues. If this Table's Database is set up to autom
- Dismiss Database Sync Spinner
Tool to manually set the initial sync status of a Database and corresponding tables to complete. Use when you need to dismiss the synchronization spinner for a database after initial setup.
- Get Action
Tool to retrieve a Metabase action by ID. Use when you need to fetch details about a specific action including its configuration, parameters, and metadata.
- Get Action Execute Parameters
Tool to fetch values for filling in action execution parameters. Use when you need to get parameter values for executing an action by providing PK parameters and values to select.
- Get All Alerts
Tool to retrieve all alerts in Metabase. Use when you need to get a list of all configured alerts with their settings and notification channels.
- Get all Metabase actions
Tool to retrieve all actions available in the Metabase instance. Actions are entities that let you build custom forms and business logic with parameterized SQL that writes back to your database. Returns an array of action objects including
- Get Automagic Dashboard Candidates
Tool to retrieve automagic dashboard candidates for a specific database. Use when you need to discover interesting tables and schemas for automatic dashboard generation. Returns an array of schema candidates with their tables, ordered by in
- Get Automagic Dashboard Cell Analysis
Tool to return an automagic dashboard analyzing a specific cell in an entity's data. Use when you need to generate automated insights and visualizations for a cell query within a table, database, or other Metabase entity. The cell-query mus
- Get Popular Items
Tool to get the list of 5 popular items on the Metabase instance. Use when you need to discover frequently accessed dashboards or cards. Returns both dashboards and cards with their metadata including name, description, parent collection, a
- Get Recent Activity Views
Tool to retrieve recently viewed items in Metabase. Use when you need to get a list of cards, dashboards, collections, tables, or documents that the authenticated user has recently accessed. Returns metadata including timestamps and permiss
- Rescan Table Field Values
Tool to manually trigger an update for FieldValues for Fields belonging to a specific Table. Use when you need to refresh field value caches after table data changes. Only applies to Fields that are eligible for FieldValues.
- Run Card Pivot Query
Tool to run a pivot table query on a Metabase card (question). Use when you need to execute the query associated with a specific card and get results formatted for pivot table visualization. The response includes data rows, column metadata,
- Run Card Query
Tool to run the query associated with a Card and return its results. Use when you need to execute a card's query with optional parameters and cache control.
- Run Dashboard Pivot DashCard Query
Tool to run a pivot table query for a specific DashCard. Use when you need to execute a pivot table query on a dashboard card with optional parameter filters.
- Save Dashboard to Collection
Tool to save a denormalized dashboard description into a collection. Use when you need to create a new dashboard directly in a specific collection with full configuration including cards, tabs, and parameters.
- Search Dataset Parameter Values
Tool to search for parameter values in datasets when editing cards or dashboards. Use when you need to provide autocomplete functionality for parameters. Expects a query string and returns matching values.
- Sync Table Schema
Tool to trigger a manual update of the schema metadata for a specific Table. Use when you need to refresh table schema information after database changes. This synchronizes columns, data types, and other metadata from the underlying databas
- Trigger Database Field Values Rescan
Tool to trigger a manual scan of field values for a Database. Use when you need to refresh field values for filter dropdowns after data changes. Requires superuser permissions.
- Trigger Database Schema Sync
Tool to trigger a manual update of the schema metadata for a Database. Use when you need to refresh the database schema metadata in Metabase after structural changes.
- Unpersist Card
Tool to unpersist a Metabase card/model. Deletes the persisted table backing the model and all queries after this will use the card's query rather than the saved version. Use when you need to remove persistence from a model.
- Update Field Values
Tool to update field values and human-readable values for a Field whose semantic type is category/city/state/country or whose base type is type/Boolean. Use when you need to set or update the distinct values for a field along with optional
Setup
Setup guide
- 11. In Metabase, navigate to Settings → Admin → People, select your user, and generate a new API key with read and write permissions. 2. Copy the key to your clipboard. 3. In Switchy, open the Integrations panel from the left sidebar and search for Metabase. 4. Click Connect, paste your API key, and enter your Metabase instance URL (e.g., https://analytics.yourcompany.com). 5. Click Authorize — Switchy will verify the connection by fetching your user profile. 6. Open any Project, type '@Metabase list my bookmarks' in the chat, and confirm you see a response listing your saved items. 7. If the test fails, double-check the URL format and confirm your API key hasn't expired in Metabase settings.
What teammates see: by default, memories from Metabase are scoped to the Project (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.
Works well with
Top models
Compatibility data appears once enough Projects have used this MCP together with a given model.
How Switchy teams use it
Starter prompts
Weekly Metrics Snapshot
@Metabase show me all dashboards in the 'Weekly KPIs' collection and summarize the main metrics from each oneOpen in a Project →
Clone Dashboard for Testing
@Metabase copy the 'Sales Pipeline' dashboard to a new one called 'Sales Pipeline - Q2 Test' in the Experiments collectionOpen in a Project →
Bookmark Sprint Reports
@Metabase bookmark the 'Sprint Velocity' card and the 'Bug Backlog' dashboard for meOpen in a Project →
Refresh Cached Data
@Metabase delete the cache for database ID 5 so we're working with today's dataOpen in a Project →
Clean Up Old Actions
@Metabase list all actions in the 'Legacy Workflows' collection and delete any that haven't been used in 90 daysOpen in a Project →
Example outputs
Illustrative - representative of the model's voice and quality, not literal recordings.
@Metabase show me all dashboards in the 'Sales Analytics' collection and summarize what each one tracks
Found 4 dashboards in the Sales Analytics collection: 1. **Q4 Revenue Overview** – Tracks quarterly revenue by region, product line, and sales rep. Includes conversion funnel and deal velocity metrics. 2. **Pipeline Health** – Monitors open opportunities, weighted pipeline value, and stage distribution. Updated daily. 3. **Customer Cohort Analysis** – Visualizes retention rates and LTV by acquisition month. Covers 24-month cohorts. 4. **Sales Team Performance** – Individual quota attainment, activity metrics, and win rates by rep. All dashboards were last modified within the past 2 weeks and are shared with the Sales team.
This example demonstrates the MCP's ability to retrieve and organize dashboard metadata from Metabase collections. Requires read access to the specified collection. The AI synthesizes raw dashboard properties (name, description, cards) into a human-readable summary—actual field names and chart types will vary by your Metabase setup.
@Metabase copy the 'Monthly Revenue' dashboard to the 'Executive Reports' collection and rename it 'Board Deck - Revenue'
Dashboard copied successfully. The new dashboard 'Board Deck - Revenue' is now available in the Executive Reports collection (ID: 47). The copy includes all 8 cards from the original dashboard: revenue trend line, regional breakdown table, YoY comparison bar chart, and 5 supporting KPI cards. Filters and parameters were preserved. The dashboard URL is https://metabase.yourcompany.com/dashboard/152. Note: The copy is a shallow duplicate—cards reference the same underlying questions. Edits to card queries will affect both dashboards unless you clone the questions separately.
Showcases the MCP's write capability for dashboard management. Requires write access to the target collection. The 'shallow copy' behavior is important: the new dashboard reuses existing question cards rather than duplicating them, so query changes propagate. Use this for quick templating; for full isolation, you'd need to copy questions first.
@Metabase bookmark the 'Customer Churn Analysis' dashboard and clear the API cache for our production database so fresh data loads
Completed both actions: 1. **Bookmark created** – 'Customer Churn Analysis' dashboard (ID: 89) is now bookmarked for your account. It will appear in your pinned items on the Metabase home screen. 2. **Cache cleared** – Invalidated all cached query results for the Production PostgreSQL database (ID: 3). Next dashboard or question load will fetch live data from the source. Note that clearing cache may temporarily slow query performance as Metabase rebuilds result sets. Both operations completed in under 2 seconds.
Demonstrates chaining two distinct tools in one prompt: user-scoped bookmarking and database-level cache management. Cache clearing is a privileged operation—requires admin or database write access. Use cautiously in production; clearing cache during peak hours can spike database load as queries re-execute without cached results.
Use-case deep-dives
When the Metabase MCP beats manual dashboard updates
A 6-person ops team runs weekly exec reviews where they copy last week's dashboard, swap in fresh data sources, and archive the old version. The Metabase MCP's Copy Dashboard and Delete API Cache tools let Switchy automate this in one prompt: "Clone last week's revenue dashboard, update the date filter to this week, and clear the cache." The MCP handles all 50+ available tools, so you can also bookmark the new version or delete stale actions without switching contexts. This works cleanly if your team runs fewer than 20 dashboards—beyond that, the tool list gets noisy and you'll want a dedicated Metabase admin workflow instead. If your execs need the same 3-5 dashboards refreshed on a schedule, this MCP saves 15 minutes per week and keeps the whole team in one Switchy thread.
Why this MCP isn't the right call for live support queries
A 3-person support team fields customer questions that often require pulling usage stats from Metabase—things like "How many times did this account run Report X last month?" The Metabase MCP can technically fetch data, but it's built for dashboard management, not ad-hoc querying. You'll spend more time writing prompts to navigate collections and cards than you would just opening Metabase in a browser tab. The MCP shines when you're *building* or *organizing* dashboards (copying, bookmarking, deleting), not when you need a quick answer from an existing report. If your support flow is "check the same 5 dashboards 20 times a day," bookmark those in Metabase itself and skip the MCP. Save Switchy + Metabase for the monthly ritual of cloning last quarter's board or cleaning up deprecated actions.
When 50 tools justify the API key setup
A 10-person data team inherits 200+ Metabase dashboards after an acquisition, half of them stale or duplicates. The Metabase MCP's Delete Action, Delete Bookmark, and Copy Dashboard tools let Switchy batch-process the cleanup: "Delete all actions tagged 'deprecated', remove bookmarks for dashboards older than 18 months, and copy the 5 active revenue dashboards into a new 'Q1 2025' collection." The API key auth is one-time setup, and the 50-tool catalog means you can chain operations without switching between Metabase's UI and Switchy. This scenario justifies the MCP because the work is infrequent (quarterly), high-volume (hundreds of items), and benefits from conversational orchestration. If you're only touching 10 dashboards, the manual UI is faster. At 50+ items, Switchy + this MCP turns a 2-hour slog into a 15-minute thread.
Frequently asked
What can Switchy do with the Metabase MCP?
Switchy can manage your Metabase analytics workspace through 50 tools covering dashboards, questions, bookmarks, collections, and field configurations. The MCP lets you copy dashboards, create bookmarks for quick access, configure field dimensions for better data presentation, and clear API caches. It's built for teams that want to automate Metabase admin tasks without clicking through the web UI.
Do I need admin access to connect Metabase to Switchy?
You need a Metabase API key with permissions matching what you want Switchy to do. Creating or deleting actions requires write access; copying dashboards needs dashboard edit rights; clearing cache typically needs admin. Generate the key in your Metabase account settings, then paste it into Switchy's connection flow. The MCP respects your Metabase role permissions.
Can the Metabase MCP run SQL queries or create new questions?
No. This MCP focuses on workspace management — copying dashboards, organizing bookmarks, configuring field settings, and clearing caches. If you need to run queries or build questions, use Metabase's native interface or its separate query API. Switchy's MCP is for teams automating the admin layer, not the analytics layer.
Why use this instead of Metabase's web UI or REST API?
Use the MCP when you want conversational access to Metabase admin tasks inside Switchy's shared workspace. Instead of writing API scripts or clicking through menus, you describe what you need — "copy the Q4 dashboard to the exec collection" — and Switchy handles the tool calls. The web UI is still better for building questions; the MCP is better for bulk operations and team workflows.
Who on my team should connect the Metabase integration?
Whoever manages your Metabase workspace and has an API key with the right permissions. Typically a data lead or admin. Once connected in Switchy, anyone in your workspace can ask Switchy to perform Metabase tasks, but the actions run under the connected account's permissions. One connection per workspace is enough; you don't need every analyst to connect their own key.