MCP server for LOINC (Logical Observation Identifiers Names and Codes) API access with Code Mode execution, GraphQL/SPARQL support, and API catalog search
Three tools with partial schemas and descriptions. loinc_search has a well-structured Zod schema with typed parameters (query: string, category: optional string, max_results: optional number) and a detailed description (194 chars) explaining usage in loinc_execute. However, loinc_execute and loinc_query_data lack visible input schemas in the provided source, only descriptions are shown. The descriptions are present but generic (loinc_execute: 'Execute JavaScript code...', loinc_query_data: 'Query staged data...'). No output schemas documented. No error handling guidance. No parameter validation rules or constraints visible. Tool composition is reasonable (search → execute → query), but parameter descriptions lack detail on expected formats, constraints, or recovery paths.
Execute JavaScript code against the LOINC API. Code runs in a sandboxed V8 isolate with: - searchSpec(query) — search the API catalog - listCategories() — list endpoint categories - getEndpoint(path) — get full endpoint docs - api.get(path, params) for GET requests - api.post(path, body, params) for POST requests - console.log() capture The last expression or return value is the result.
Query staged data from auto-staged large responses using SQL
Search the LOINC API catalog. Returns matching endpoints with full parameter docs. Use this to discover API capabilities before calling loinc_execute. Categories: (varies by catalog) USAGE IN loinc_execute: - api.get(path, params) for GET, api.post(path, body, params) for POST - Path params like /lookup/{id} are auto-interpolated from params: api.get('/lookup/{id}', {id: 'ENSG...'}) - Remaining params become query string - Large responses (>100KB) are auto-staged: check result.__staged, return the staging info, use loinc_query_data to explore - Use limit/pagination params to control response size. Large datasets auto-stage for SQL queries.
loinc_execute and loinc_query_data lack visible input schemas. Only descriptions provided; no Zod/JSON Schema definitions found in source.
No output schemas documented for any tool. LLMs cannot infer what fields to expect or plan downstream calls.
Parameter descriptions lack format constraints, ranges, or validation rules. E.g., 'code' in loinc_execute has no guidance on syntax, size limits, or error recovery.
No error handling guidance. Descriptions do not explain what errors are retryable, user-fixable, or fatal, or how to recover.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 36 | 2026-07-28+ | v2 |
loinc_execute description mentions 'sandbox' and 'V8 isolate' but does not explain timeout behavior, resource limits, or what happens if code runs too long.