Summarize a saved question’s data
Inspect a question and execute it to summarize actual result rows.
Run saved Metabase question [question]. Summarize [business question] and mention any limits on the results reviewed.
Leina connects to Metabase to help you run saved reports, summarize business data, and inspect dashboards. Ask in your team chat. Leina does the work and brings back the result.
Connect Metabase, choose what to share, and hand off your first task.
You
Run our saved “Orders by channel” question [question identifier]. Summarize which channels contributed the most orders.
Leina
I ran the saved question and summarized the channel mix from its results.
Metabase · Report summary
Orders by channel
A concise view of the saved report’s results.
A Metabase AI agent runs accessible saved questions and explains their results in business terms, keeping the reporting scope clear.
You specify the source and the destination. Leina uses the content available to your connection and returns the result for you to review.
Metabase helps teams explore data through saved questions, charts, and dashboards.
Visit Provider Website ↗Provide the saved question you want to review.
Read its definition and retrieve the results.
Summarize the figures within the available result set.
Copy a prompt, add your details, and send it to Leina in your connected team chat.
Inspect a question and execute it to summarize actual result rows.
Run saved Metabase question [question]. Summarize [business question] and mention any limits on the results reviewed.
Your next Metabase task can start with a message.
Tell Leina what you need in your team chat. Include the source, destination, and expected result.
Connect a Metabase API key and public HTTPS instance URL.
Share the source material, say where the result belongs, and describe what you need.
Review the result and any changes in the connected app.
Hand off these everyday tasks to your AI employee.
Get the Metabase user associated with the API key.
List Metabase databases visible to the API key.
Retrieve one Metabase database by ID.
List Metabase collections visible to the API key.
Retrieve one Metabase collection by ID.
List Metabase cards, also known as questions.
Retrieve one Metabase card by ID.
List Metabase dashboards visible to the API key.
Retrieve one Metabase dashboard by ID.
Search Metabase content visible to the API key.
Discover the tools exposed by this Metabase instance's native MCP server. Without toolNames, returns a compact index (name, one-line summary, annotations); pass toolNames to get the full descriptions and input schemas of those tools before calling them with call_tool. Tool names and schemas follow the instance's Metabase version.
Call a native Metabase MCP tool with JSON arguments matching the inputSchema returned by list_tools with toolNames. Depending on the tool, this can run queries or create, update, or archive Metabase content as the API key's user; check the tool's annotations and confirm writes first.
Discover native MCP resources. Data resources can be read with read_mcp_resource; MCP Apps (ui://) resources are not supported.
Read a text resource listed by list_mcp_resources. MCP Apps (ui://) resources are not supported.
Connect the Apps your work depends on, and give Leina the context to carry the task forward.
Hand off a task while your team is discussing it. Leina uses your connected tools and brings the result back to the conversation.
See How Leina Works in SlackI ran the saved question and summarized the channel mix from its results.
Discover the tools exposed by your instance with list_tools, then inspect the selected tool inputSchema for supported query parameters.
Result limits and pagination follow the native tool exposed by your Metabase version. Read any returned paging hints before drawing conclusions.
Metabase’s native MCP features must be available and enabled for these query operations.
Start with one task you already need to do. Tell Leina what a finished result should look like.
Connect Metabase, choose what to share, and hand off your first task.