Schemaflow MCP Server

Real-time PostgreSQL schema access for AI-IDEs via Model Context Protocol (MCP)

Local serverstdioGo

What is the Schemaflow MCP server?

Schemaflow mcp server lets Claude, Cursor and other MCP clients work with Schemaflow directly. Real-time PostgreSQL schema access for AI-IDEs via Model Context Protocol (MCP).

What Schemaflow does

SchemaFlow MCP Server provides your AI-IDE with live access to PostgreSQL and Supabase database schemas through the Model Context Protocol. Get real-time schema context for smarter code generation in tools like Cursor, Windsurf, and VS Code + Cline.

Tools it exposes

Once connected, the assistant can call these 3 tools directly:

  • get_schema — Retrieves complete database schema information including tables, columns, relationships, functions, triggers, enums, and indexes from PostgreSQL or Supabase
  • analyze_database — Performs comprehensive database analysis including performance insights, security assessment, and structural recommendations for PostgreSQL and Supabase
  • check_schema_alignment — Validates your PostgreSQL or Supabase schema against best practices and identifies potential issues with actionable recommendations

Installing the schemaflow mcp server

Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.

Where it fits

Database servers turn schema archaeology and ad-hoc reporting into conversation, which is why they tend to be the second or third server people install. Schemaflow sits in that group, and the shape of its toolset — get_schema, analyze_database, check_schema_alignment — tells you what it is really for. Worth comparing against the other databases servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • Maintained by CryptoRadi, written in Go.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the schemaflow mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
get_schemaRetrieves complete database schema information including tables, columns, relationships, functions, triggers, enums, and indexes from PostgreSQL or Supabase databases.
analyze_databasePerforms comprehensive database analysis including performance insights, security assessment, and structural recommendations for PostgreSQL and Supabase databases.
check_schema_alignmentValidates your PostgreSQL or Supabase schema against best practices and identifies potential issues with actionable recommendations.

How to install the Schemaflow MCP server

{
  "mcpServers": {
    "schemaflow": {
      "type": "sse",
      "url": "https://api.schemaflow.dev/mcp/?token=your-token-here"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Schemaflow to get schema.
  • Use Schemaflow to analyze database.
  • Use Schemaflow to check schema alignment.

Frequently asked questions

It connects Schemaflow to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (get_schema, analyze_database, check_schema_alignment) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Schemaflow directly.