Lightdash MCP server

What the model can do

Lightdash (Cloud or self-hosted): projects, a search over charts, dashboards and spaces, each project's dashboards, charts, spaces, explores (the metrics model) and scheduled deliveries, and a chart's versions; can create, rename and delete spaces, create, duplicate and delete dashboards, delete or roll back charts, send, pause, resume or delete scheduled deliveries, refresh a project's dbt build and comment on dashboard tiles.

Reads

• lightdash_projectsLightdash projects in the organisation: uuid, name, warehouse type and when created.
• lightdash_search_contentSearch Lightdash charts, dashboards and spaces by name, across projects or within one: uuid, type, name, description, project, space, who created it…
• lightdash_dashboardsDashboards in one Lightdash project: uuid, name, description, space, last updated, views, and the kinds of tiles on it.
• lightdash_chartsSaved charts in one Lightdash project: uuid, name, description, space, the dashboard it belongs to, chart kind, last updated and views.
• lightdash_spacesSpaces (folders) in one Lightdash project: uuid, name, path, and how many charts, dashboards and child spaces each holds.
• lightdash_exploresExplores in one Lightdash project: the tables and models in its semantic layer that charts are built from, by name, label and group…
• lightdash_schedulersScheduled deliveries in one Lightdash project: uuid, name, whether enabled, cron and timezone, format, the chart or dashboard delivered…
• lightdash_chart_versionsA saved chart's version history: each version's uuid, when it was made and by whom.

Acts, when you ask

These change something in Lightdash. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.

• lightdash_create_spaceCreate a space (folder) in a Lightdash project, at the top level or inside a parent space.
• lightdash_rename_spaceRename a Lightdash space.
• lightdash_delete_spacePermanently delete a Lightdash space, with the charts, dashboards and child spaces in it.
• lightdash_create_dashboardCreate an empty Lightdash dashboard in a project (tiles are added in Lightdash), or, with duplicate_from…
• lightdash_delete_dashboardPermanently delete a Lightdash dashboard (by uuid or slug); it disappears for everyone and cannot be undone.
• lightdash_delete_chartPermanently delete a saved Lightdash chart (by uuid or slug).
• lightdash_rollback_chartRestore a saved Lightdash chart to an earlier version (from lightdash_chart_versions).
• lightdash_send_scheduler_nowSend a scheduled delivery now to every target on it (email addresses, which may be outside the company, Slack, Teams or Google Chat channels…
• lightdash_set_scheduler_enabledPause (enabled false) or resume (enabled true) a scheduled delivery.
• lightdash_delete_schedulerPermanently delete a scheduled delivery; its recipients stop receiving it.
• lightdash_refresh_projectRefresh a Lightdash project's dbt build (pull and recompile the models) so explores pick up model changes.
• lightdash_comment_on_dashboard_tileAdd a comment to a tile on a Lightdash dashboard, as the token's user.

Connect it

First connect Lightdash on Dashboard → Connections, then add Memtro to your client once. The Lightdash tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Lightdash connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

• › Which dashboards changed this week?
• › What charts are in the Finance space?
• › Which explores have compile errors?
• › Who created the churn dashboard, and how many views does it have?
• › Refresh the analytics project so the new orders model shows up.

Questions

Is this an official Lightdash MCP server?

No. It is Memtro's MCP server with Memtro's Lightdash connector behind it: the connector reads Lightdash through its API with the credentials you connect on Dashboard → Connections, and Lightdash publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

What does it cost?

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in Lightdash?

Only when you ask, and only what it has been granted: create a space in a project; rename a space; delete a space and what is in it, permanently; create an empty dashboard, or duplicate an existing one; delete a dashboard, permanently; delete a saved chart, permanently, which removes it from dashboards; roll a saved chart back to an earlier version; send a scheduled delivery now to all of its recipients; pause or resume a scheduled delivery; delete a scheduled delivery, permanently; refresh a project's dbt build so explores pick up model changes; comment on a dashboard tile, optionally mentioning people. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.

Which clients work?

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

Other MCP servers · Analytics

• Google Analytics 4 MCP server
• Plausible Analytics MCP server
• Umami MCP server
• Google Search Console MCP server
• Segment MCP server
• App Store Connect MCP server