Azure Translator MCP Server with EntraID authentication and Blob Storage persistence for document and text translation
Server has 10 tools with complete input schemas and descriptions. Naming follows verb_noun convention (start_, check_, get_, detect_, translate_, upload_, list_). Descriptions are present and actionable (avg ~120 chars). However, output schemas are not documented, responses are inferred from code (e.g., ListOneDriveFilesTool returns text content, not structured fields). Parameter descriptions are adequate but lack constraint details (e.g., 'language code' without format examples). Error handling returns text messages but lacks recovery guidance. No tool annotations (readOnlyHint, destructiveHint). Security: credentials injected server-side (good), but no audit logging visible. Composition is sound, tools are single-purpose and chainable (e.g., start_document_translation → check_translation_status → get_translation_result).
Check any Azure Translator job status directly (bypasses local job store)
Check the status of a document translation job by job ID. Returns current status and progress information.
Detect the language of the provided text using Azure Translator
Get list of languages supported by Azure Translator
Get the result of a completed document translation job. Downloads the translated document to OneDrive and provides download links.
List files and folders in OneDrive for Business
Output schemas not documented. Tools return text content or unstructured responses. LLMs cannot plan downstream calls or extract structured data reliably.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). LLMs cannot distinguish safe reads from destructive writes without explicit hints.
Error responses lack recovery guidance. CheckAzureJobTool returns 'Job Not Found' but does not suggest next steps (e.g., 'Try check_translation_status() with a known job ID').
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 54 | 2026-07-28+ | v2 |
Start a document translation job and return a job ID for monitoring. Use this for async translation to avoid timeouts in Copilot Studio.
Translate a complete document (Word, PDF, Excel, etc.) using Azure Translator and save the result to OneDrive. Supports formats: .docx, .xlsx, .pptx, .pdf, .html, .txt, .rtf, .odt, .ods, .odp, .xlf, .xliff
Translate text from one language to another using Azure Translator. Supports 137 languages with automatic language detection. Use language codes like "fr" (French), "es" (Spanish), "de" (German), etc.
Upload a file from local filesystem to Azure Blob Storage
Parameter descriptions lack format constraints. 'language code' does not specify format (e.g., 'ISO 639-1 two-letter code like "fr", "es", "de"'). LLMs may pass invalid values.
No pagination support documented. list_onedrive_files accepts limit but no cursor/offset for continuation. Large result sets may exceed context window.