SchemaFlow MCP server

Provides real-time PostgreSQL schema access through cloud-based caching, delivering cached database structure information including tables, columns, relationships, functions, triggers, enums, and indexes with schema validation and performance insights.
Back to servers
Provider
SchemaFlow
Release date
Jun 02, 2025
Language
Go
Stats
1 star

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

Getting Started

1. Get Your MCP Token

Visit the SchemaFlow Dashboard to:

  • Connect your PostgreSQL or Supabase database
  • Load and cache your schema
  • Generate an MCP token

2. Configure Your AI-IDE

For Cursor IDE:

  1. Open Cursor Settings
  2. Go to Features → MCP
  3. Click "Add New MCP Server"
  4. Use this configuration:
{
  "name": "schemaflow",
  "type": "sse",
  "url": "https://api.schemaflow.dev/mcp/?token=your-token-here"
}

For Windsurf IDE:

Add to your MCP configuration:

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

For VS Code + Cline:

Configure in Cline's MCP settings:

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

Available MCP Tools

get_schema

Retrieves complete database schema information including tables, columns, relationships, functions, triggers, enums, and indexes from PostgreSQL or Supabase databases.

Parameters:

  • query_type (optional): Filter specific information (tables, columns, relationships, functions, triggers, enums, indexes, all)

Example AI queries:

  • "Show me my database schema"
  • "What tables do I have?"
  • "Show me all relationships"
  • "List database functions"

analyze_database

Performs comprehensive database analysis including performance insights, security assessment, and structural recommendations for PostgreSQL and Supabase databases.

Example AI queries:

  • "Analyze my database performance"
  • "Check database security"
  • "Review database structure"
  • "Give me a database overview"

check_schema_alignment

Validates your PostgreSQL or Supabase schema against best practices and identifies potential issues with actionable recommendations.

Example AI queries:

  • "Check schema alignment"
  • "Validate my database"
  • "Any schema issues?"
  • "Check naming conventions"

How It Works

  1. Schema Caching: When you load your schema in SchemaFlow dashboard, it's automatically cached for MCP access
  2. Secure Connection: Your AI-IDE connects using MCP with secure token authentication
  3. Real-time Access: Your AI assistant can query schema data in real-time for better code generation

Security Features

  • Schema metadata only - No actual data is accessed or stored
  • Token-based authentication - Each user has a unique, revokable token
  • Encrypted connections - All MCP communication is encrypted
  • User-specific access - Tokens only access your own cached schema data

Additional Resources

For detailed setup instructions, troubleshooting, and advanced configuration, visit the Complete MCP Integration Guide.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later