schema-sieve-mcp
# schema-sieve-mcp
Schema Sieve is a local MCP tool for understanding JSON Schema files while planning tests. It focuses on the part that usually takes the most time: finding required paths, nested constraints, unions, arrays, and likely sensitive fields before writing fixtures.
## Tools
- `inspect_schema`: summarize types, properties, required fields, constraints, composition, and references.
- `plan_fixture`: produce placeholder paths such as `<string>`, `<integer>`, and `<string:date-time>` without inventing or copying test data.
## Safety
- Only local JSON files are accepted.
- Paths are bounded by `SCHEMA_SIEVE_ROOT`, which defaults to the workspace parent when launched from the package.
- Files are capped at 2 MB and results are bounded.
- Examples, defaults, constants, and sensitive-like property names are omitted or marked as omitted.
- This is structural guidance, not a JSON Schema validator and not a security scanner.
## Run
```bash
npm install
npm run build
node dist/index.js
```
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: inspect_schema provides a summary/description of the schema, while plan_fixture creates a placeholder plan for test fields. There is no overlap in their responsibilities.
Both tool names follow a consistent verb_noun pattern (inspect_schema, plan_fixture), using the same underscore style and analogous structure. The naming is predictable and coherent.
With only two tools, the set is on the thin side. While each tool serves a distinct purpose and fits a narrow domain, the count is at the lower boundary of what is typically considered well-scoped.
The tools cover the core workflow of inspecting a schema and planning fixtures without exposing example data. Minor gaps exist, such as a tool to validate or compare schemas, but the two tools together provide a coherent, non-redundant surface for the stated purpose.