Supabase

Created By
supabase-communitya year ago
Overview

What is Supabase MCP?

Supabase MCP (Model Context Protocol) is a server that connects your Supabase projects to various AI assistants like Cursor and Claude, enabling them to perform tasks such as managing tables, fetching configurations, and querying data.

How to use Supabase MCP?

To use Supabase MCP, you need to install Node.js, create a personal access token in your Supabase settings, and configure your MCP client to connect to the Supabase MCP server using the provided access token.

Key features of Supabase MCP?

  • Connects AI assistants directly with Supabase projects.
  • Standardizes communication between Large Language Models (LLMs) and external services.
  • Supports various operations like managing projects, executing SQL queries, and deploying edge functions.

Use cases of Supabase MCP?

  1. Automating database management tasks through AI assistants.
  2. Enhancing application functionality by integrating AI capabilities.
  3. Streamlining project configurations and migrations with AI assistance.

FAQ from Supabase MCP?

  • What is the Model Context Protocol?

    It is a standard that defines how LLMs communicate with external services like Supabase.

  • Is there a cost associated with using Supabase MCP?

    The usage of Supabase MCP is subject to the pricing of your Supabase account and the resources you utilize.

  • Can I restrict access to specific projects?

    Yes, you can scope the MCP server to a specific project using the --project-ref flag.

Server Config

{
  "mcpServers": {
    "supabase": {
      "command": "npx",
      "args": [
        "-y",
        "@supabase/mcp-server-supabase@latest",
        "--access-token",
        "sbp_03799d9799696a22107bda0918e527e9888b0fa3"
      ]
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
supabase-community
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago