PlanetScale MCP server

What the model can do

PlanetScale databases: databases with their kind, region and plan, branches, deploy requests (schema changes) with their state, approval and reviews, backups, the heaviest or slowest query patterns on a branch, and invoices; when you ask, can create or delete a branch, open, review or approve, deploy, cancel, close, apply, revert or skip the revert of a deploy request, and take or delete a backup.

Reads

• planetscale_list_databasesPlanetScale databases in the organization: name, kind (mysql, postgresql, neki), state, plan, region, default branch, branch counts…
• planetscale_list_branchesBranches of a PlanetScale database: name, production or development, state, parent, region, safe migrations, deletion protection and cluster size.
• planetscale_list_deploy_requestsDeploy requests (schema changes from one branch into another) for a PlanetScale database: number, state, deployment state, approved, branches…
• planetscale_get_deploy_requestOne PlanetScale deploy request with its deployment's progress and its reviews (comment or approval, text and date; reviewers are not named).
• planetscale_list_backupsBackups of a PlanetScale branch: name, state, size, estimated storage cost, policy, and when it ran and expires.
• planetscale_query_insightsQuery patterns on a PlanetScale branch from Insights, by default the ones taking the most total time over the last day: normalized SQL, tables…
• planetscale_list_invoicesPlanetScale invoices for the organization: total, billing period, paid and overdue.

Acts, when you ask

These change something in PlanetScale. 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.

• planetscale_create_branchCreates a development branch of a PlanetScale database from parent_branch (default the database's default branch), copying its schema…
• planetscale_delete_branchPermanently deletes a PlanetScale branch and its data; it cannot be undone.
• planetscale_create_deploy_requestOpens a PlanetScale deploy request proposing branch's schema changes into into_branch…
• planetscale_review_deploy_requestReviews a PlanetScale deploy request as the service token: state commented leaves a comment…
• planetscale_deploy_deploy_requestDeploys a PlanetScale deploy request, queuing its schema change to run against the target branch (often production).
• planetscale_cancel_deploy_requestCancels a queued PlanetScale deployment before it runs; the deploy request stays open.
• planetscale_close_deploy_requestCloses a PlanetScale deploy request without deploying it.
• planetscale_apply_deploy_requestCompletes a gated PlanetScale deployment that is waiting to cut over, switching the target branch (often production) to the new schema.
• planetscale_revert_deploy_requestReverts a deployed PlanetScale schema change during its revert period, putting the target branch's schema back as it was.
• planetscale_skip_revertEnds a deployed PlanetScale schema change's revert period now, after which it can no longer be reverted.
• planetscale_create_backupTakes a backup of a PlanetScale branch now, kept for the retention given (or the default); backup storage is billed.
• planetscale_delete_backupPermanently deletes a PlanetScale backup; it cannot be undone.

Connect it

First connect PlanetScale on Dashboard → Connections, then add Memtro to your client once. The PlanetScale 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 PlanetScale 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 deploy requests are open on the main database?
• › What are the slowest queries on production over the last day?
• › When did the last backup of production run?
• › Is our latest invoice paid?
• › Create a development branch called add-orders-index.

Questions

Is this an official PlanetScale MCP server?

No. It is Memtro's MCP server with Memtro's PlanetScale connector behind it: the connector reads PlanetScale through its API with the credentials you connect on Dashboard → Connections, and PlanetScale 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 PlanetScale?

Only when you ask, and only what it has been granted: create a branch; delete a branch; open a deploy request from one branch into another; comment on or approve a deploy request; deploy a deploy request (queue its schema change); cancel a queued deploy request; close a deploy request without deploying it; apply a gated deploy request (cut over); revert a deployed schema change; skip the revert period of a deployed schema change; take a backup of a branch; delete a backup. 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 · Databases and warehouses

• Postgres MCP server
• MySQL and MariaDB MCP server
• SQL Server MCP server
• BigQuery MCP server
• Snowflake MCP server
• AWS Athena MCP server