Official elvix SDK MCP server for AI coding agents to integrate elvix authentication, identity, and account management. Provides dynamic tools from elvix API manifest with read-only and admin modes.
All three tools have identical, generic parameter schemas with no type specificity. Descriptions are minimal (under 50 chars) and do not explain WHEN to use each tool or what distinguishes them. No parameter descriptions exist, 'body' and 'query' are bare object types with only placeholder text. No output schemas documented. Tools appear to be thin HTTP proxies rather than agent-optimized interfaces. No error handling guidance. Naming follows HTTP verb convention but lacks semantic clarity about the elvix domain.
GET /api/v1/verify — calls GET /api/v1/verify on the configured elvix origin.
POST /api/v1/device/approve — calls POST /api/v1/device/approve on the configured elvix origin.
POST /api/v1/session — calls POST /api/v1/session on the configured elvix origin.
All three tools use identical generic parameter schemas: {body: object, query: object} with no type specificity, constraints, or field documentation. LLMs cannot determine what fields to pass or what values are valid.
Descriptions are under 50 characters and do not explain WHEN to use each tool, what it returns, or how it differs from similar tools. 'GET /api/v1/verify, calls GET /api/v1/verify...' is circular and adds no semantic value.
No output schemas documented. LLMs cannot plan downstream tool calls or extract required fields (e.g., userId, token, status) from responses.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 31 | 2026-07-28+ | v2 |
Parameter descriptions are placeholder text only ('JSON request body, when applicable', 'Query parameters'). No guidance on required fields, formats, constraints, or examples.
No error handling guidance. Tools do not document what errors are possible, whether they are retryable, or what the LLM should do next on failure.