What kind of dashboard is this?

Depends on the server. Metabase builds BI dashboards over your data; Mixpanel builds product-analytics views like funnels and retention; Axiom builds observability dashboards from JSON. The create call is the same idea on each: turn saved queries or charts into a board people can open.

How does this pair with listing dashboards?

Creating makes a new board; listing finds existing ones. An agent often lists first to check whether a dashboard already covers what it needs, and only creates a new one if none does, which keeps the workspace from filling with near-duplicate boards.

MCP servers that can create a dashboard

3 verified servers expose a tool that can create a dashboard

When an agent has set up monitoring or wired up data, the dashboard is how a human sees it. Creating one assembles the panels into a view, so the metrics, the funnels, the charts live somewhere a person can open rather than buried in a query.

These verified servers let an agent create a dashboard.

Top pick

Metabase

Cognition

Community

A maintained Metabase MCP server from Cognition that lets an agent run questions, build dashboards, and query databases across your Metabase instance.

data-analytics57

Tool:

create_dashboard

Metabase's create_dashboard assembles BI charts over your connected data into a saved board a team can open.

Pick 2

Mixpanel

Official

Mixpanel's official hosted MCP server lets an agent query events, funnels, retention, and dashboards and manage metrics, experiments, and feature flags.

data-analytics

Tool:

Create-Dashboard

On Mixpanel, Create-Dashboard builds a product-analytics view, the funnels and retention charts a team watches.

Pick 3

Axiom

Official

Axiom's official remote MCP server lets agents query logs, traces, and metrics with APL and manage datasets, monitors, and dashboards over OAuth.

monitoring-observability

Tool:

createDashboard

Axiom creates a dashboard from a JSON definition through createDashboard, fitting an agent that defines observability views as code.

What to know

A dashboard turns scattered queries into a standing view, and creating one is the step that makes an agent's analysis durable for the people who read it. The three servers build different kinds: Metabase assembles BI charts over your connected data, Mixpanel builds product-analytics views like funnels and retention, Axiom creates one from a JSON definition for observability. What they share is the move from ad-hoc query to saved board, the thing a teammate opens next week without re-running anything.

A dashboard an agent creates is a lasting artifact, so it pays to remember it rather than rebuild. An agent that recreates the same board every session leaves duplicates a team has to sort through. Holding the dashboard's id and what it shows lets the agent update the existing one instead of cluttering the workspace with near-copies.

Questions

What kind of dashboard is this?: Depends on the server. Metabase builds BI dashboards over your data; Mixpanel builds product-analytics views like funnels and retention; Axiom builds observability dashboards from JSON. The create call is the same idea on each: turn saved queries or charts into a board people can open.
How does this pair with listing dashboards?: Creating makes a new board; listing finds existing ones. An agent often lists first to check whether a dashboard already covers what it needs, and only creates a new one if none does, which keeps the workspace from filling with near-duplicate boards.