schemaflow

SchemaFlow MCP Server

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

Command

claude mcp add --transport stdio cryptoradi-schemaflow-mcp-server npx -y schemaflow-mcp-server \
  --env TOKEN="your-token-here" \
  --env MCP_ENDPOINT="https://api.schemaflow.dev/mcp"

How to use

SchemaFlow MCP Server exposes real-time access to your PostgreSQL or Supabase schemas for AI-assisted IDEs via the Model Context Protocol (MCP). Once you obtain an MCP token from the SchemaFlow dashboard, configure your IDE to connect to the hosted MCP endpoint and start querying schema data in real time. Use the available tools to retrieve complete schema details, analyze your database, and validate schema alignment, all without exposing actual data.

To use the tools, connect your IDE via the provided SSE URL and token. With the get_schema tool, you can request tables, columns, relationships, functions, and other schema artifacts. The analyze_database tool offers performance and security insights, while check_schema_alignment returns actionable recommendations. These capabilities are designed to help AI-based code assistants generate accurate, context-aware queries and migrations by leveraging live schema metadata rather than static snapshots.

How to install

Prerequisites:

Node.js (v14+ recommended) or an environment that can run npx

Step-by-step:

Install Node.js from https://nodejs.org/ if you don’t already have it.
Open a terminal and install/run the MCP server client via npx using the provided package name: npx -y schemaflow-mcp-server
When prompted, supply the necessary environment variables (token and endpoint) or export them in your shell before running: export TOKEN=your-token-here export MCP_ENDPOINT=https://api.schemaflow.dev/mcp
If you prefer to pass env vars inline, you can run: TOKEN=your-token-here MCP_ENDPOINT=https://api.schemaflow.dev/mcp npx -y schemaflow-mcp-server
In your IDE, configure the MCP server entry with the provided URL/token and select the schemaflow MCP configuration (e.g., for Cursor, Windsurf, or VS Code + Cline).

Additional notes

Tips and common issues:

Ensure your token has access to the cached schema data in your SchemaFlow dashboard.
The MCP URL is regional; use the endpoint shown in your dashboard to avoid latency.
If you see authentication errors, double-check the TOKEN value and that it has not expired or been revoked.
This MCP server only exposes schema metadata (no actual data); ensure your security rules reflect your intended access scope.
When using multiple IDEs, prefer issuing unique tokens per IDE to maintain per-user isolation.
Refer to the Complete MCP Integration Guide at schemaflow.dev/mcp-guide for troubleshooting and advanced settings.

Related MCP Servers

zen

1.1k

Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage

MCP -Deepseek_R1

A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)

mcp-fhir

A Model Context Protocol implementation for FHIR

mcp

Inkdrop Model Context Protocol Server

mcp-appium-gestures

This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..

dubco -npm

The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.