Read-only MCP server that brings FirmaUY signature inspection to your AI assistant. Offline, no smart card, no signing, redacted by default.
Two tools with clear, domain-specific purposes and reasonable descriptions (inspect: 156 chars, validate_cedula: 95 chars). Both have documented input schemas with type and description fields. However, output schemas are not visible in the source code provided, only input schemas are shown. Parameter descriptions are present but minimal (e.g., 'Path to the signed file' lacks format/constraint details). No error handling guidance, no parameter validation rules, and no recovery hints documented. Tool names follow verb_noun pattern (inspect, validate_cedula) appropriately for read-only operations. Missing: output schema documentation, error classification, and actionable error messages.
Verify a signature on a file and report what was signed, by whom, when, and whether the signature is valid.
Validate a Uruguayan cédula (national ID) check digit.
Output schemas not documented. LLMs cannot plan downstream tool calls or extract structured data without knowing what fields to expect from inspect() and validate_cedula().
Parameter descriptions lack format/constraint details. 'Path to the signed file' does not specify accepted file types (PDF, XML, ASiC), character limits, or path format. 'A Uruguayan cédula number' does not clarify format (digits only? with/without hyphens?) or length.
No error handling guidance. Tools do not document what errors can occur (invalid file, corrupted signature, malformed cédula), how to classify them (retryable vs user-fixable), or what the LLM should do next.
Missing parameter constraints. 'original' parameter in inspect is optional but no enum or pattern validates file paths. LLMs may pass invalid paths without guidance on format.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 56 | 2026-07-28+ | v2 |
No documentation of what inspect() returns (signature validity, signer name, timestamp, etc.). Without output schema, LLMs cannot extract or reason about verification results.