MCP server for interacting with MySQL databases based on Node
Single tool 'mysql_query' with critical deficiencies. Input schema present but severely underdescribed: 'sql' parameter lacks format constraints, length limits, or usage guidance. Tool description is generic and does not explain WHEN to use it, what it returns, or how to handle destructive operations. No output schema documented. No error handling guidance. No parameter validation rules stated. Destructive operations (INSERT, UPDATE, DELETE, DDL) exposed without confirmation or dry-run pattern. Schema-specific permissions mentioned in description but not reflected in parameters or documented return structure.
Run SQL queries against MySQL database (Multi-DB mode enabled) with support for: INSERT, UPDATE, DELETE, DDL and READ operations (Schema-specific permissions enabled)
No output schema documented. Tool description does not specify what fields are returned, data types, or structure. LLM cannot plan downstream operations or extract required data.
Destructive operations (DELETE, UPDATE, INSERT, DDL) exposed without confirmation, dry-run, or idempotent hint. No error guidance for failed mutations. Agents can cause irreversible data loss.
Input parameter 'sql' lacks description of format, constraints, or valid SQL types. No mention of supported operations, length limits, or injection prevention. LLM cannot infer valid input.
Tool description mentions 'Schema-specific permissions enabled' but no parameters expose or document how permissions are applied. Unclear how multi-DB mode affects behavior or what the agent should expect.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 32 | <=2025-11-25 | v2 |
No error handling guidance. Tool will fail on invalid SQL, permission denials, or connection errors, but LLM has no recovery path. No actionable error messages specified.