Model Context Protocol server for Xano database integration. Compatible with Smithery for AI agent integration.
All 7 tools have basic descriptions and input schemas, but quality is inconsistent. Tool names follow verb_noun convention (list_, get_, browse_). However, descriptions are minimal (10-50 chars), parameter descriptions are sparse or missing, output schemas are undocumented, and error handling is absent. No tool annotations (readOnlyHint, destructiveHint). Parameter naming has inconsistencies: xano_list_tables uses 'database_name' but xano_get_table_details uses 'workspace_id' for the same concept. No pagination guidance despite browse_table_content accepting pagination. Schemas present but lack detail on return types and field structure.
Browse table content with pagination and filtering support.
Get details for a specific Xano instance.
Get details for a specific Xano table.
Get details for a specific Xano workspace.
List all databases (workspaces) in a specific Xano instance.
List all Xano instances associated with the account.
Output schemas completely undocumented. No tool returns a documented schema, LLMs cannot predict response structure or plan downstream calls. Baseline: 100% of A+ tools document return types.
Parameter descriptions missing or trivial. 'instance_name' described as 'The name of the Xano instance' (tautological). No guidance on format, constraints, or when to use. Baseline: 100% of A+ tools have param descriptions.
Inconsistent parameter naming for same concept. xano_list_tables uses 'database_name' but xano_get_table_details uses 'workspace_id' for the workspace identifier. Forces LLM to reason about field mappings.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 51 | <=2025-11-25 | v2 |
List all tables in a specific Xano database (workspace).
No error handling guidance. Code returns generic error dicts with 'error' key but no recovery hints. LLM cannot determine if error is retryable, user-fixable, or fatal.
No tool annotations. All tools are read-only but lack readOnlyHint annotation. Agents cannot distinguish safe tools from destructive ones without explicit hints.