Gives Claude five schema operations: generating JSON Schema from sample data with automatic type inference and enum detection, converting JSON or schemas into TypeScript interfaces, validating data against schemas with detailed error paths, creating realistic mock data with smart field detection (emails, names, phone numbers), and diffing two schemas to identify breaking changes. Reach for this when you're working with APIs or data structures and need Claude to validate payloads, generate types for your codebase, produce test fixtures, or analyze schema evolution between versions. Runs locally via stdio, so your schemas and data stay on your machine.
MCP server providing schema validation and generation tools for AI agents.
Generate a JSON Schema from sample JSON data. Infers types, required fields, formats (email, date, URI, UUID), and detects enum patterns from multiple examples.
Generate TypeScript interfaces and types from JSON data or a JSON Schema. Handles nested objects, arrays, optional fields, enums, and union types.
Validate data against a JSON Schema with detailed error messages including JSON path, expected type, actual value, and the violated constraint keyword.
Generate realistic mock data from a JSON Schema. Smart field-name detection produces contextual values: email fields get valid emails, name fields get realistic names, phone fields get formatted numbers, etc.
Compare two JSON Schemas to find added, removed, and changed fields. Identifies type changes, constraint changes, and classifies each difference as breaking or non-breaking for backwards compatibility analysis.
npm install
npm run build
Add to your claude_desktop_config.json:
{
"mcpServers": {
"schema-tools": {
"command": "node",
"args": ["path/to/mcp-schema-tools/dist/index.js"]
}
}
}
MIT
com.mcparmory/google-sheets
domdomegg/google-sheets-mcp
henilcalagiya/google-sheets-mcp
cct15/war-dashboard-data
moooonad/mcp-google-sheets-full
io.github.br0ski777/csv-to-json