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-tools Generate a JSON Schema from the sample data I provided."
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.
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.
Related MCP server: apitype
npm install
npm run buildAdd to your claude_desktop_config.json:
{
"mcpServers": {
"schema-tools": {
"command": "node",
"args": ["path/to/mcp-schema-tools/dist/index.js"]
}
}
}MIT
Compare two JSON Schemas and identify all differences: added/removed/changed fields, type changes, constraint changes (min/max, patterns, enums). Classifies each change as breaking or non-breaking for backwards compatibility analysis.
Inputs: new_schema (required), old_schema (required).
Generate a JSON Schema from one or more sample JSON values. Infers types, required fields, formats (email, date, URI, UUID), and detects enum patterns from multiple examples.
Inputs: samples (required), title, detect_enums.
Generate TypeScript interfaces and types from JSON data or a JSON Schema. Handles nested objects, arrays, optional fields, enums, union types, and Record types.
Inputs: json, schema, root_name.
Generate realistic mock data from a JSON Schema. Uses smart field-name detection to produce contextual values: email fields get valid emails, name fields get realistic names, dates get ISO strings, etc. Supports all JSON Schema types and constraints.
Inputs: schema (required), seed, count.
Validate data against a JSON Schema. Returns detailed error messages with JSON path, expected type, actual value, and the violated keyword (type, required, format, pattern, minimum, etc.).
Inputs: data (required), schema (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 5 tools
Each tool has a clearly distinct purpose: generation from data, generation from schema, validation, mocking, and diffing. No overlap or ambiguity between tool responsibilities, so an agent should reliably select the correct tool for a given task.
All tool names follow a consistent verb_noun pattern (generate_, validate_, mock_, diff_). The verbs are specific and descriptive, and the noun consistently refers to the primary artifact (schema or types). No mixed conventions or vague naming.
With exactly 5 tools covering the core schema lifecycle, the count is tight and focused. Each tool earns its place, and the number is within the ideal range for a utility server without being overly minimal or bloated.
The set covers the major schema operations: creating schemas from data, generating types for coding, validating data, generating mocks, and comparing schemas for evolution. Together they form a coherent, end-to-end toolkit with no obvious dead ends or missing critical operations.
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.
Generate a typed SDK, CLI, and MCP server from any OpenAPI or GraphQL spec, and keep them current.
Deploy production REST APIs from JSON schemas in seconds. Manage projects, schemas, and deployments.
