This server converts schemas and generates/validates data via MCP tools.
schema_convert: Convert SQL DDL, Prisma, or JSON into Zod schemas, TypeScript interfaces, or Pydantic v2 models (optionally all formats).
schema_generate_mock: Generate realistic synthetic mock JSON data (names, emails, dates, UUIDs, etc.) from a schema, with configurable record count.
schema_validate: Validate a JSON payload against a schema definition and report missing fields or type mismatches.
Accepts Prisma schema files as input and converts them to Zod schemas, TypeScript interfaces, or Pydantic models, and can generate mock data from them.
Generates Python Pydantic v2 models from SQL DDL, Prisma schemas, or JSON input.
Generates TypeScript interfaces and type definitions from SQL DDL, Prisma schemas, or JSON input.
Generates Zod validation schemas from SQL DDL, Prisma schemas, or JSON input.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Schema Bridge MCP Server @Schema Bridge MCP Server convert this SQL schema to TypeScript types"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Model Context Protocol (MCP) Server & CLI for Instant Schema Conversion & Mock API Generation.
Effortlessly compile SQL DDL, Prisma schemas, and JSON into Zod validation schemas, TypeScript interfaces, and Python Pydantic v2 models, plus generate synthetic mock datasets in seconds.
Converting database schemas into API validation rules, TypeScript types, and synthetic testing data is repetitive, tedious, and error-prone.
schema-bridge-mcp gives Claude Desktop, Cursor, Command Code, and Cline native superpowers to automate schema translations and mock generation on demand.
Related MCP server: mock-mcp
.cursor/mcp.json){
"mcpServers": {
"schema-bridge": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/schema-bridge-mcp/dist/index.js"]
}
}
}claude_desktop_config.json){
"mcpServers": {
"schema-bridge": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/schema-bridge-mcp/dist/index.js"]
}
}
}Tool | Parameters | Description |
|
| Ingests SQL DDL ( |
|
| Generates realistic, contextual synthetic mock datasets (UUIDs, names, emails, dates, prices, statuses) strictly respecting your field types. |
|
| Compares runtime JSON payloads against database schemas and flags missing fields or mismatched types instantly. |
# Clone & install dependencies
git clone https://github.com/rafim-dev/schema-bridge-mcp.git
cd schema-bridge-mcp
npm install
npm run build
# Convert SQL DDL to Zod Schema
node dist/index.js convert "CREATE TABLE users (id UUID PRIMARY KEY, email TEXT, is_active BOOLEAN);" zod
# Convert Prisma to TypeScript interfaces
node dist/index.js convert schema.prisma typescript
# Generate 5 realistic mock records
node dist/index.js mock "CREATE TABLE orders (id INT, total FLOAT, customer_email TEXT);" 5🔄 Download Compiled Zero-Config Bundle on Gumroad ($5.00+ Pay-What-You-Want)
🎮 Download on itch.io ($5.00+ Pay-What-You-Want)
🎁 Get the 2-in-1 AI Developer Power Bundle (Includes schema-bridge-mcp + mcp-smart-git at 20% off)
MIT License. Authored by rafim_dev.
Convert any database schema (SQL DDL, Prisma) or JSON payload into production-ready Zod schemas, TypeScript interfaces, or Python Pydantic v2 models.
Inputs: schemaInput (required), targetFormat (required), entityName.
Generate realistic, relational synthetic mock JSON data (names, emails, dates, UUIDs, currencies, statuses) from any SQL, Prisma, or JSON schema.
Inputs: schemaInput (required), count, entityName.
Validate a JSON data payload against a schema definition (SQL, Prisma, or JSON Schema) and report detailed type errors and missing fields.
Inputs: dataPayload (required), schemaInput (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool has a distinct purpose: validating data, converting schemas, and generating mock data. There is no overlap or ambiguity between them.
All tools follow the consistent pattern `schema_<verb>`, using clear snake_case naming. The action is immediately identifiable from the name.
Three tools cover a focused schema-related workflow without unnecessary bloat or missing essentials. The count is well-suited to the server's stated purpose.
The toolset covers the core lifecycle of schema handling: validation, conversion, and mock generation. No significant gaps are apparent for the described domain.
Generate realistic, FK-consistent synthetic test data for your databases from your AI assistant.
The AI that understands raw data: Schema over your tables and databases, as MCP tools.
Convert, lint and generate LLM tool schemas for OpenAI, Anthropic, Gemini and MCP
Convert JSON samples into TypeScript interfaces and Zod schemas, with inference caveats.
