
Schema
io.github.rog0xPublished by GitHub account rog0xv1.0.1Updated Oct 24, 2026
JSON Schema, TypeScript types, mocks for AI agents
Overview
Lets an assistant generate, validate, mock, and diff JSON Schemas and TypeScript types from sample JSON data.
- What you can do
- Provides five tools for schema work: generate_json_schema infers a JSON Schema from sample JSON, detecting types, required fields, formats such as email, date, URI and UUID, and enum patterns across multiple examples. generate_typescript produces TypeScript interfaces and types from JSON data or a schema, handling nested objects, arrays, optional fields, enums and unions. validate_schema checks data against a schema and reports JSON path, expected type, actual value and the violated constraint. mock_from_schema creates realistic sample data using field-name detection, and diff_schemas compares two schemas, flagging added, removed and changed fields and classifying differences as breaking…
- When to use it
- Useful when an assistant needs to derive a schema or TypeScript types from example payloads, check that data conforms to a schema, produce test fixtures, or review whether a schema change breaks backwards compatibility.
- Requirements
- Runs locally as a stdio process, installed from the npm package @rog0x/mcp-schema-tools; the README setup builds it with npm install and npm run build, and Claude Desktop is configured to launch the built dist/index.js with node. No authentication, environment variables or headers are declared.
Installation
In SourceWeft
- Open Schema in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
mcp-schema-tools
MCP server providing schema validation and generation tools for AI agents.
Tools
generate_json_schema
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
Generate TypeScript interfaces and types from JSON data or a JSON Schema. Handles nested objects, arrays, optional fields, enums, and union types.
validate_schema
Validate data against a JSON Schema with detailed error messages including JSON path, expected type, actual value, and the violated constraint keyword.
mock_from_schema
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.
diff_schemas
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.
Setup
Usage with Claude Desktop
Add to your claude_desktop_config.json:
License
MIT
Source: README.md at commit 215f5a3
Tools
0Version history
1- v1.0.1LatestSep 16, 2026
Score
40% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.