Server profile

Supabase MCP Server

Connect AI assistants to Supabase projects for SQL, schema changes, debugging, and Edge Functions. Hosted HTTP setup supports project scoping, read-only access, and selectable feature groups.

Server facts

Supabase MCP Server

Tech

Runtime / language
node
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
2,955
Last commit
Data as of

Tags

  • Database Migrations
  • Edge Functions
  • Postgresql
  • Read Only
  • Supabase

Overview

Supabase MCP Server connects development assistants to Supabase project administration and database work. Its tools span schema inspection, SQL queries, tracked migrations, documentation search, advisory checks, and application configuration. Other groups expose Edge Function source and deployment, project lifecycle operations, and development branches. TypeScript types can be generated from a project's database schema, giving an assistant information it can use while building application code. The hosted service uses an HTTP endpoint, and compatible clients guide users through signing in to the appropriate Supabase organization.

Access can be narrowed before the assistant starts working. Project scoping limits the connection to one project and removes account-level operations. Read-only mode disables mutating tools and executes SQL with a read-only Postgres user. Feature selection further restricts which tool groups are visible; storage tools are disabled by default to reduce the tool count. These controls matter because the integration can otherwise perform consequential changes, including migrations and deployments. The README recommends reviewing its security guidance before connecting a project. Local Supabase CLI and self-hosted environments also offer MCP access, but with fewer tools and without OAuth 2.1. Branching is described as experimental and dependent on a paid plan. The server is still pre-1.0, so the documented interface may change between versions.

Install & configure

Requirements

  • A Supabase account with access to the intended organization
  • An MCP client supporting hosted HTTP connections

No install command stated in the README — see repo.

No runnable server launch command is stated in the provided README. Configure the hosted URL and complete the client login flow. The README recommends project_ref scoping and read_only=true.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

A supported configuration example is not available for this client and transport. Check the client documentation for its connection flow; do not substitute an undocumented JSON format.

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "supabase-mcp": {
      "url": "https://mcp.supabase.com/mcp"
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "supabase-mcp": {
      "type": "http",
      "url": "https://mcp.supabase.com/mcp"
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "supabase-mcp": {
      "serverUrl": "https://mcp.supabase.com/mcp"
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "supabase-mcp": {
      "type": "http",
      "url": "https://mcp.supabase.com/mcp"
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository tool metadata and repository README. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
search_docsSearch current Supabase documentation through a GraphQL request.
list_organizationsFind organizations associated with the signed-in user.
get_organizationInspect organization details, including its subscription plan.
list_projectsFind Supabase projects available to the user.
get_projectInspect one project's details and status.
get_costLook up organization-specific pricing before creating a project or branch.
confirm_costRecord user confirmation of the cost returned for a project or branch.
create_projectCreate a Supabase project after organization and cost confirmation.
pause_projectSuspend an existing project's operation.
restore_projectBring a paused project back into operation.
list_tablesInspect tables in selected schemas, optionally expanding structural details.
list_extensionsInspect installed database extensions.
list_migrationsInspect the database's tracked migration history.
apply_migrationApply SQL schema changes as a recorded database migration.
execute_sqlRun database SQL for data queries rather than tracked schema changes.
query_logsQuery a project's unified log stream with read-only ClickHouse SQL.
get_logsRetrieve a project's logs for a selected service.
get_advisorsRetrieve security and performance advisory notices for a project.
get_project_urlRetrieve a project's API endpoint address.
get_publishable_keysRetrieve client-safe publishable and legacy anonymous project keys.
generate_typescript_typesCreate TypeScript definitions reflecting a project's database schema.
list_edge_functionsInspect the Edge Functions deployed to a project.
get_edge_functionRead the files belonging to an Edge Function.
deploy_edge_functionDeploy a new Edge Function or update one with a new version.
create_branchCreate a development database branch with production migrations but without production data.
list_branchesInspect development branches and their operation status.
delete_branchRemove a development branch.
merge_branchPromote a branch's migrations and Edge Functions into production.
reset_branchReset branch migrations, discarding untracked schema or data changes.
rebase_branchApply newer production migrations to a development branch.
list_storage_bucketsInspect the storage buckets available in a project.
get_storage_configRead project storage settings.
update_storage_configChange project storage settings; the README requires a paid plan.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Inspect project tables and run data queries.
  • Apply tracked SQL migrations during development.
  • Investigate project logs and security or performance advisories.
  • Generate TypeScript types and deploy Edge Functions.
  • Manage development branches when the plan supports them.

Strengths

  • Combines database work, debugging, documentation, and function deployment.
  • Offers project-scoped access, read-only operation, and feature filtering.
  • Hosted setup uses client-guided authentication.

Limitations

  • Broad access can mutate project data and infrastructure unless restricted.
  • Branching is experimental and requires a paid plan.
  • Local and self-hosted MCP variants provide fewer tools and lack OAuth 2.1.

Frequently asked questions

Yes. Set project_ref on the connection URL. This also removes account-level tools such as project and organization listings.

It disables mutating tools and runs execute_sql through a read-only Postgres user.

No. Storage tools are disabled by default; the features URL parameter lets you select the groups you want.

The CLI exposes a local MCP endpoint, but the README says local and self-hosted variants have a smaller toolset and no OAuth 2.1.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

Neon MCP Server

Databases

Manage Neon Postgres projects, branches, queries, and migrations through an AI assistant. The hosted MCP service supports OAuth or API keys, read-only access, and project-level scoping.

MCP Toolbox for Databases

Databases

MCP Toolbox for Databases connects agents and IDEs to enterprise data through prebuilt tools or custom query definitions. It combines database access with connection pooling, authentication integration, and observability.

MCP Server for MySQL

Databases

MCP Server for MySQL lets Claude and other AI clients inspect schemas and execute SQL. It defaults to read-only access, with optional write flags, SSH tunneling, multi-database support, and result redaction.

DBHub

Databases

DBHub exposes SQL execution and database discovery through a small MCP interface. It spans five database engines, supports multiple configured connections, and includes a web workbench for use without an assistant.

Postgres MCP Pro

Databases

Give assistants PostgreSQL schema access, SQL execution, health checks, and performance analysis. Postgres MCP Pro adds query plans and hypothetical index evaluation with configurable read-only operation.

MySQL MCP Server

Databases

Expose MySQL schema inspection, data samples, and SQL execution to MCP assistants. It supports multi-database access, optional SSH tunnels, and local or network deployment, with database permissions controlling available operations.

MongoDB MCP Server

Databases

MongoDB MCP Server connects AI clients to MongoDB databases and Atlas. Its tools cover queries, schema inspection, database changes, and MongoDB knowledge searches, with read-only launch examples for safer exploration.

Query MCP for Supabase

Databases

Query MCP connects coding assistants to Supabase SQL, schema changes, project management, and user administration. It includes SQL risk controls, but its author has stopped active maintenance.