Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Nativ

REMOTE · MCP.USENATIV.COM · 2 COMPONENTS

Localize text, images, audio and subtitles with brand voice, memory and style guides.

+6 this week 79 Trust /100

Last scanned (20 hours ago)

Scores higher than 74% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Design and Media

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security83
Transport & Reachability100
Schema Quality & AI Usability68
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 6998 tokens (~137/item across 51 items; 51 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management40
  • Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 52 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 +4
    • Schema quality: pass → fail ▼ functional
    • Tool coverage: 0% → 100% ▲ functional
    • “add_translation_memory_entry” reworded the description of “name” cosmetic
    • “add_translation_memory_entry” reworded the description of “source_language_code” cosmetic
    • “add_translation_memory_entry” reworded the description of “source_text” cosmetic
    • “add_translation_memory_entry” reworded the description of “target_language_code” cosmetic
    • “add_translation_memory_entry” reworded the description of “target_text” cosmetic
    • “check_image_cultural_fit” reworded the description of “countries” cosmetic
    • “check_image_cultural_fit” reworded the description of “image_path” cosmetic
    • “clone_voice” reworded the description of “confirm_ownership” cosmetic
    • “clone_voice” reworded the description of “consent_path” cosmetic
    • “clone_voice” reworded the description of “language_code” cosmetic
    • “clone_voice” reworded the description of “reference_path” cosmetic
    • “create_byo_voice” reworded the description of “clip_ranges” cosmetic
    • “create_byo_voice” reworded the description of “clip_reference” cosmetic
    • “create_byo_voice” reworded the description of “confirm_ownership” cosmetic
    • “create_byo_voice” reworded the description of “consent_path” cosmetic
    • “create_byo_voice” reworded the description of “language_code” cosmetic
    • “create_byo_voice” reworded the description of “name” cosmetic
    • “create_byo_voice” reworded the description of “reference_path” cosmetic
    • “create_style_guide” reworded the description of “content” cosmetic
    • “create_style_guide” reworded the description of “is_enabled” cosmetic
    • “create_style_guide” reworded the description of “title” cosmetic
    • “delete_saved_voice” reworded the description of “voice_id” cosmetic
    • “delete_style_guide” reworded the description of “guide_id” cosmetic
    • “delete_subtitle” reworded the description of “storage_path” cosmetic
    • “delete_translation_memory_entry” reworded the description of “entry_id” cosmetic
    • “export_subtitle” reworded the description of “output_path” cosmetic
    • “export_subtitle” reworded the description of “qc” cosmetic
    • “export_subtitle” reworded the description of “regenerate” cosmetic
    • “export_subtitle” reworded the description of “source_language” cosmetic
    • “export_subtitle” reworded the description of “storage_path” cosmetic
    • “extract_image_text” reworded the description of “image_path” cosmetic
    • “get_subtitle_download_url” reworded the description of “storage_path” cosmetic
    • “get_subtitle_review” reworded the description of “storage_path” cosmetic
    • “get_voice_consent_script” reworded the description of “language_code” cosmetic
    • “list_translation_memory_entries” reworded the description of “enabled_only” cosmetic
    • “list_translation_memory_entries” reworded the description of “information_source” cosmetic
    • “list_translation_memory_entries” reworded the description of “limit” cosmetic
    • “list_translation_memory_entries” reworded the description of “offset” cosmetic
    • “list_translation_memory_entries” reworded the description of “search” cosmetic
    • “list_translation_memory_entries” reworded the description of “source_language_code” cosmetic
    • “list_translation_memory_entries” reworded the description of “target_language_code” cosmetic
    • “list_voices” reworded the description of “language_code” cosmetic
    • “localize_image” reworded the description of “image_path” cosmetic
    • “localize_image” reworded the description of “num_images” cosmetic
    • “localize_image” reworded the description of “output_format” cosmetic
    • “localize_image” reworded the description of “output_path” cosmetic
    • “localize_image” reworded the description of “replacements” cosmetic
    • “localize_image” reworded the description of “target_language_code” cosmetic
    • “localize_subtitle_file” reworded the description of “context” cosmetic
    • “localize_subtitle_file” reworded the description of “glossary” cosmetic
    • “localize_subtitle_file” reworded the description of “storage_path” cosmetic
    • “localize_subtitle_file” reworded the description of “target_languages” cosmetic
    • “localize_subtitles” reworded the description of “context” cosmetic
    • “localize_subtitles” reworded the description of “formality” cosmetic
    • “localize_subtitles” reworded the description of “glossary_path” cosmetic
    • “localize_subtitles” reworded the description of “output_dir” cosmetic
    • “localize_subtitles” reworded the description of “source_language_code” cosmetic
    • “localize_subtitles” reworded the description of “subtitle_path” cosmetic
    • “localize_subtitles” reworded the description of “target_language_codes” cosmetic
    • “localize_subtitles” reworded the description of “video_path” cosmetic
    • “parse_subtitle” reworded the description of “file_path” cosmetic
    • “preview_voice” reworded the description of “language_code” cosmetic
    • “preview_voice” reworded the description of “output_path” cosmetic
    • “preview_voice” reworded the description of “text” cosmetic
    • “preview_voice” reworded the description of “voice_id” cosmetic
    • “register_video” reworded the description of “file_path” cosmetic
    • “remux_video” reworded the description of “audio_path” cosmetic
    • “remux_video” reworded the description of “output_path” cosmetic
    • “remux_video” reworded the description of “video_id” cosmetic
    • “reorder_style_guides” reworded the description of “guide_ids” cosmetic
    • “search_translation_memory” reworded the description of “limit” cosmetic
    • “search_translation_memory” reworded the description of “min_score” cosmetic
    • “search_translation_memory” reworded the description of “query” cosmetic
    • “search_translation_memory” reworded the description of “source_language_code” cosmetic
    • “search_translation_memory” reworded the description of “target_language_code” cosmetic
    • “submit_translation_feedback” reworded the description of “approved” cosmetic
    • “submit_translation_feedback” reworded the description of “feedback” cosmetic
    • “submit_translation_feedback” reworded the description of “language” cosmetic
    • “submit_translation_feedback” reworded the description of “result” cosmetic
    • “submit_translation_feedback” reworded the description of “source” cosmetic
    • “synthesize_audio” reworded the description of “keep_background_music” cosmetic
    • “synthesize_audio” reworded the description of “keep_same_length” cosmetic
    • “synthesize_audio” reworded the description of “language” cosmetic
    • “synthesize_audio” reworded the description of “language_code” cosmetic
    • “synthesize_audio” reworded the description of “output_path” cosmetic
    • “synthesize_audio” reworded the description of “segments” cosmetic
    • “synthesize_audio” reworded the description of “source_duration_ms” cosmetic
    • “synthesize_audio” reworded the description of “source_transcript” cosmetic
    • “synthesize_audio” reworded the description of “stem_id” cosmetic
    • “synthesize_audio” reworded the description of “video_id” cosmetic
    • “synthesize_audio” reworded the description of “video_output_path” cosmetic
    • “synthesize_audio” reworded the description of “voice_id” cosmetic
    • “synthesize_audio_advanced” reworded the description of “document_translation” cosmetic
    • “synthesize_audio_advanced” reworded the description of “enterprise_long_form” cosmetic
    • “synthesize_audio_advanced” reworded the description of “keep_background_music” cosmetic
    • “synthesize_audio_advanced” reworded the description of “keep_same_length” cosmetic
    • “synthesize_audio_advanced” reworded the description of “language” cosmetic
    • “synthesize_audio_advanced” reworded the description of “language_code” cosmetic
    • “synthesize_audio_advanced” reworded the description of “output_path” cosmetic
    • “synthesize_audio_advanced” reworded the description of “segments” cosmetic
    • “synthesize_audio_advanced” reworded the description of “source_duration_ms” cosmetic
    • “synthesize_audio_advanced” reworded the description of “source_transcript” cosmetic
    • “synthesize_audio_advanced” reworded the description of “speaker_voices” cosmetic
    • “synthesize_audio_advanced” reworded the description of “speech_islands” cosmetic
    • “synthesize_audio_advanced” reworded the description of “stem_id” cosmetic
    • “synthesize_audio_advanced” reworded the description of “video_id” cosmetic
    • “synthesize_audio_advanced” reworded the description of “video_output_path” cosmetic
    • “synthesize_audio_advanced” reworded the description of “voice_id” cosmetic
    • “transcribe_audio” reworded the description of “file_path” cosmetic
    • “transcribe_audio” reworded the description of “keep_background_music” cosmetic
    • “transcribe_audio” reworded the description of “source_language_code” cosmetic
    • “transcribe_audio_detailed” reworded the description of “enterprise_long_form” cosmetic
    • “transcribe_audio_detailed” reworded the description of “file_path” cosmetic
    • “transcribe_audio_detailed” reworded the description of “keep_background_music” cosmetic
    • “transcribe_audio_detailed” reworded the description of “source_language_code” cosmetic
    • “transcribe_audio_detailed” reworded the description of “speaker_count” cosmetic
    • “translate” reworded the description of “backtranslate” cosmetic
    • “translate” reworded the description of “context” cosmetic
    • “translate” reworded the description of “formality” cosmetic
    • “translate” reworded the description of “glossary” cosmetic
    • “translate” reworded the description of “max_characters” cosmetic
    • “translate” reworded the description of “source_language” cosmetic
    • “translate” reworded the description of “source_language_code” cosmetic
    • “translate” reworded the description of “target_language” cosmetic
    • “translate” reworded the description of “target_language_code” cosmetic
    • “translate” reworded the description of “text” cosmetic
    • “translate_batch” reworded the description of “context” cosmetic
    • “translate_batch” reworded the description of “formality” cosmetic
    • “translate_batch” reworded the description of “source_language” cosmetic
    • “translate_batch” reworded the description of “source_language_code” cosmetic
    • “translate_batch” reworded the description of “target_language” cosmetic
    • “translate_batch” reworded the description of “target_language_code” cosmetic
    • “translate_batch” reworded the description of “texts” cosmetic
    • “translate_dialogue” reworded the description of “context” cosmetic
    • “translate_dialogue” reworded the description of “formality” cosmetic
    • “translate_dialogue” reworded the description of “segments” cosmetic
    • “translate_dialogue” reworded the description of “source_language” cosmetic
    • “translate_dialogue” reworded the description of “source_language_code” cosmetic
    • “translate_dialogue” reworded the description of “speakers” cosmetic
    • “update_language_custom_style” reworded the description of “custom_style” cosmetic
    • “update_language_custom_style” reworded the description of “mapping_id” cosmetic
    • “update_language_formality” reworded the description of “formality” cosmetic
    • “update_language_formality” reworded the description of “mapping_id” cosmetic
    • “update_style_guide” reworded the description of “content” cosmetic
    • “update_style_guide” reworded the description of “guide_id” cosmetic
    • “update_style_guide” reworded the description of “is_enabled” cosmetic
    • “update_style_guide” reworded the description of “title” cosmetic
    • “update_subtitle_review” reworded the description of “storage_path” cosmetic
    • “update_subtitle_review” reworded the description of “updates” cosmetic
    • “update_translation_memory_entry” reworded the description of “enabled” cosmetic
    • “update_translation_memory_entry” reworded the description of “entry_id” cosmetic
    • “update_translation_memory_entry” reworded the description of “target_text” cosmetic
    • “upload_style_guide” reworded the description of “file_path” cosmetic
    • “upload_style_guide” reworded the description of “title” cosmetic
    • “upload_subtitle” reworded the description of “auto_localize” cosmetic
    • “upload_subtitle” reworded the description of “context” cosmetic
    • “upload_subtitle” reworded the description of “file_path” cosmetic
    • “upload_subtitle” reworded the description of “glossary” cosmetic
    • “upload_subtitle” reworded the description of “source_language” cosmetic
    • “upload_subtitle” reworded the description of “target_languages” cosmetic
    • “parse_audio_script” reworded the description of “file_path” cosmetic
  • 18 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Nov 26 +1
    • Stability: unverified → 0.03 ▲ functional
  • 9 Nov 26 70

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://mcp.usenativ.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.usenativ.com CN=WR3,O=Google Trust Services,C=US 13 Oct 2026 11 Jan 2027 RSA 2048 SHA256-RSA 378e03c3d7536ae90ab86da1bc0e6128
SANs: mcp.usenativ.com
CN=WR3,O=Google Trust Services,C=US (CA) CN=GTS Root R1,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 RSA 2048 SHA256-RSA 7ff005a91568d63abc22861684aa4b5a
CN=GTS Root R1,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 19 Jun 2020 28 Jan 2028 RSA 4096 SHA256-RSA 77bd0d6cdb36f91aea210fc4f058d30d

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.usenativ.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
usenativ.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Challenged, unverified

The endpoint asked for a token, but we could not retrieve and validate the RFC 9728 metadata that tells a client how to obtain one.

Result Challenged, unverified
Enforced On tool calls
HTTP status 200

Protected resource metadata

Retrieved No
Problem No resource metadata

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.usenativ.com/mcp Verified 200
http (plaintext) http://mcp.usenativ.com/mcp HTTPS enforced 302 https://mcp.usenativ.com/mcp
MCP tools · 51 exposed · ~6,961 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
add_translation_memory_entry ~186

Add a new entry to the translation memory. Use this to store approved translations so they are reused in future localizations. Args: source_text: The original text. target_text: The approved translation. source_language_code: Source language code (e.g. "en"). target_language_code: Target language code (e.g. "fr-FR"). name: Optional label for this entry (e.g. "homepage hero copy").

NameTypeReqDescription
namestring–Optional label for this entry (e.g. "homepage hero copy").
source_language_codestringyesSource language code (e.g. "en").
source_textstringyesThe original text.
target_language_codestringyesTarget language code (e.g. "fr-FR").
target_textstringyesThe approved translation.
NameTypeReqDescription
resultstringyes–

No examples provided.

check_image_cultural_fit ~183

Analyze an image for cultural-sensitivity issues across markets before launch. Returns a SAFE / NOT SAFE verdict and, where relevant, the specific countries affected with the issue and a concrete fix. Args: image_path: Public HTTPS URL (hosted) or local path (stdio) to a PNG, JPEG, or WebP image. countries: Optional comma-separated list of countries to check against (e.g. "Saudi Arabia, Japan, France"). Defaults to the top markets by GDP.

NameTypeReqDescription
countriesstring–Optional comma-separated list of countries to check against (e.g. "Saudi Arabia, Japan, France"). Defaults to the top markets by GDP.
image_pathstringyesPublic HTTPS URL (hosted) or local path (stdio) to a PNG, JPEG, or WebP image.
NameTypeReqDescription
resultstringyes–

No examples provided.

clone_voice ~201

Create a Google voice clone from reference speech and spoken consent. Requires the user's explicit ownership/permission confirmation. Obtain the required consent wording with get_voice_consent_script. Inputs are local paths in stdio or public HTTPS URLs hosted. Returns voice_id for preview_voice and synthesize_audio. For a saved ElevenLabs clone from original video speech, use create_byo_voice with clip_reference=true.

NameTypeReqDescription
confirm_ownershipboolean–True only after the user explicitly confirms ownership or the speaker’s permission to clone this voice.
consent_pathstringyesSpoken consent recording: local path in stdio or public HTTPS URL when hosted. Required for Google voice cloning.
language_codestring–Language code, for example "en" or "fr". Leave empty to use the operation default.
reference_pathstringyesReference speech file: local path in stdio or public HTTPS URL when hosted.

Structured output declared, but exposes no named fields.

No examples provided.

create_byo_voice ~309

Create and save a reusable voice clone in the caller's workspace. Set clip_reference=true to clone original speech from audio/video with ElevenLabs. Optional clip_ranges selects speech-only {start_ms,end_ms} ranges, useful for individual speakers. Otherwise Google cloning needs consent_path with the speaker's consent recording. Requires explicit user confirmation of ownership/permission; never assume it. Inputs are local paths (stdio) or public HTTPS URLs (hosted). Returns voice_id for preview_voice and synthesize_audio. list_voices includes saved clones.

NameTypeReqDescription
clip_ranges––Optional speech-only ranges with integer start_ms >= 0 and end_ms > start_ms; 1–500 ranges, only with clip_reference=true.
clip_referenceboolean–True selects original-speech cloning with ElevenLabs; false selects Google cloning and requires consent_path.
confirm_ownershipboolean–True only after the user explicitly confirms ownership or the speaker’s permission to clone this voice.
consent_pathstring–Spoken consent recording: local path in stdio or public HTTPS URL when hosted. Required for Google voice cloning.
language_codestring–Language code, for example "en" or "fr". Leave empty to use the operation default.
namestring–Optional display name for the saved voice.
reference_pathstringyesReference speech file: local path in stdio or public HTTPS URL when hosted.

Structured output declared, but exposes no named fields.

No examples provided.

create_style_guide ~83

Create and save a workspace style guide used by future translations.

NameTypeReqDescription
contentstringyesStyle-guide instructions; omit/null on updates to leave them unchanged.
is_enabledboolean–Whether the style guide is enabled; omit/null on updates to leave it unchanged.
titlestringyesStyle-guide title; omit/null on updates to leave it unchanged.

Structured output declared, but exposes no named fields.

No examples provided.

delete_saved_voice ~46

Delete a saved cloned voice belonging to the caller, when explicitly requested.

NameTypeReqDescription
voice_idstringyesVoice identifier returned by list_voices or voice creation; reuse the exact identifier.

Structured output declared, but exposes no named fields.

No examples provided.

delete_style_guide ~38

Delete a workspace style guide, when explicitly requested.

NameTypeReqDescription
guide_idstringyesExact style-guide ID returned by list_style_guides.

Structured output declared, but exposes no named fields.

No examples provided.

delete_subtitle ~52

Delete a saved subtitle belonging to the caller, when explicitly requested.

NameTypeReqDescription
storage_pathstringyesExact saved subtitle storage key returned by upload_subtitle or list_subtitles; not a local path or HTTPS URL.

Structured output declared, but exposes no named fields.

No examples provided.

delete_translation_memory_entry ~39

Delete a translation memory entry, when explicitly requested.

NameTypeReqDescription
entry_idstringyesExact translation-memory entry ID returned by list_translation_memory_entries.

Structured output declared, but exposes no named fields.

No examples provided.

export_subtitle ~181

Export a saved subtitle or its QC workbook as a file/download URL. Set qc=true for the review XLSX. Otherwise retain the subtitle's original format; regenerate=true applies saved QC edits first. Use an output filename with the matching extension (.xlsx for QC).

NameTypeReqDescription
output_pathstringyesOutput filename/path in stdio, or filename for the temporary hosted download. Use the matching file extension.
qcboolean–True exports the review XLSX; false exports the subtitle in its original format.
regenerateboolean–True applies saved subtitle review edits before exporting.
source_languagestring–Source language code for subtitle processing, for example "en".
storage_pathstringyesExact saved subtitle storage key returned by upload_subtitle or list_subtitles; not a local path or HTTPS URL.

Structured output declared, but exposes no named fields.

No examples provided.

extract_image_text ~139

Extract text segments from an image, in reading order (OCR). Use this as the first step when localizing an image: pull out the on-image source strings, translate each with `translate` (so TM, style guides, and brand voice apply), then re-render with `localize_image`. Args: image_path: Public HTTPS URL (hosted) or local path (stdio) to a PNG, JPEG, or WebP image file.

NameTypeReqDescription
image_pathstringyesPublic HTTPS URL (hosted) or local path (stdio) to a PNG, JPEG, or WebP image file.
NameTypeReqDescription
resultstringyes–

No examples provided.

get_audio_capabilities ~50

Get the caller's audio/video duration limits and long-form eligibility. Check before transcription; do not assume a long input was processed fully. Respect the returned duration_ms and transcript boundaries.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

get_brand_voice ~49

Get the brand voice prompt — the core localization personality. This is the master prompt that shapes all translations. It captures the brand's tone, personality, terminology, and localization guidelines.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes–

No examples provided.

get_combined_prompt ~22

Get the workspace brand prompt combined with its enabled style guides.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

get_language_formality_options ~19

List supported workspace language formality levels.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

get_languages ~40

Get all languages configured for the Nativ workspace. Returns language names, codes, formality settings, and custom style directives for each language.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes–

No examples provided.

get_style_guides ~35

Get all style guides configured for the workspace. Returns the titles, content, and enabled status of each style guide.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes–

No examples provided.

get_subtitle_download_url ~55

Get an expiring download URL for a saved subtitle's storage path.

NameTypeReqDescription
storage_pathstringyesExact saved subtitle storage key returned by upload_subtitle or list_subtitles; not a local path or HTTPS URL.

Structured output declared, but exposes no named fields.

No examples provided.

get_subtitle_review ~55

Get saved subtitle QC rows, translations, rationales, and approval status.

NameTypeReqDescription
storage_pathstringyesExact saved subtitle storage key returned by upload_subtitle or list_subtitles; not a local path or HTTPS URL.

Structured output declared, but exposes no named fields.

No examples provided.

get_translation_memory_stats ~34

Get statistics about the translation memory. Shows total entries, enabled/disabled counts, and breakdown by source type.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes–

No examples provided.

get_voice_consent_script ~48

Get the spoken consent script required for voice cloning.

NameTypeReqDescription
language_codestring–Language code, for example "en" or "fr". Leave empty to use the operation default.
NameTypeReqDescription
resultstringyes–

No examples provided.

list_language_settings ~58

Get complete workspace language settings, including IDs for updates. Use each returned language id as mapping_id for update_language_formality or update_language_custom_style. The compact get_languages tool remains available for a human-readable summary.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

list_style_guides ~56

Get full style-guide content, IDs, enabled state and ordering for editing. The compact get_style_guides summary is unchanged. Use this complete listing to obtain guide_id for update/delete, or IDs for reorder.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

list_subtitles ~24

List the caller's saved subtitle sources, localized files, and storage paths.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

list_translation_memory_entries ~155

List and paginate translation memory entries, including IDs for editing.

NameTypeReqDescription
enabled_onlyboolean–True lists only enabled translation-memory entries.
information_sourcestring–Optional translation-memory information_source filter; empty includes all sources.
limitinteger–Maximum entries per page, 1–1000.
offsetinteger–Number of entries to skip, zero or greater.
searchstring–Optional text filter for translation-memory entries; empty disables this filter.
source_language_codestring–Source language code, for example "en"; empty omits the optional language hint/filter.
target_language_codestring–Target language code, for example "fr" or "ja".

Structured output declared, but exposes no named fields.

No examples provided.

list_voices ~61

List TTS voices available for dubbing. Args: language_code: Optional filter (e.g. "fr", "ja-JP").

NameTypeReqDescription
language_codestring–Optional filter (e.g. "fr", "ja-JP").
NameTypeReqDescription
resultstringyes–

No examples provided.

localize_image ~479

Localize an image in place by replacing its on-image text with translations. Keeps every non-text element (layout, colours, graphics) intact and re-renders the original text with the provided translations. Pair with `extract_image_text` (to get the source strings) and `translate` (to translate them with TM and brand voice) for a full image localization flow. The localized image is saved to disk and the file path is returned — the raw image bytes are not sent back to the model. Hosted mode returns a download URL instead of writing to a local path. Args: image_path: Public HTTPS URL (hosted) or local path (stdio) to a PNG, JPEG, or WebP image to localize. replacements: JSON array of {"original": "...", "translated": "..."} pairs, e.g. '[{"original": "Buy now", "translated": "Achetez maintenant"}]'. target_language_code: Target language code (e.g. "fr-FR"), used for labelling output. output_path: Optional path to write the localized image to. Defaults to "<input>.<lang>.<format>" next to the source image. num_images: Number of variants to generate (1-5, default 1). output_format: Output format — png, jpeg, or webp (default png).

NameTypeReqDescription
image_pathstringyesPublic HTTPS URL (hosted) or local path (stdio) to a PNG, JPEG, or WebP image to localize.
num_imagesinteger–Number of variants to generate (1-5, default 1).
output_formatstring–Output format — png, jpeg, or webp (default png).
output_pathstring–Optional path to write the localized image to. Defaults to "<input>.<lang>.<format>" next to the source image.
replacementsstringyesJSON array of {"original": "...", "translated": "..."} pairs, e.g. '[{"original": "Buy now", "translated": "Achetez maintenant"}]'.
target_language_codestringyesTarget language code (e.g. "fr-FR"), used for labelling output.
NameTypeReqDescription
resultstringyes–

No examples provided.

localize_subtitle_file ~166

Localize an already saved ITT subtitle file (billed), using its storage path. storage_path comes from upload_subtitle/list_subtitles, not a local path or HTTPS URL. Backend expects query parameters for this route. For SRT, use upload_subtitle(auto_localize=true) or localize_subtitles.

NameTypeReqDescription
contextstring–Optional audience, purpose and surrounding context to guide localization.
glossarystring–Optional glossary text to guide terminology for subtitle localization.
storage_pathstringyesExact saved subtitle storage key returned by upload_subtitle or list_subtitles; not a local path or HTTPS URL.
target_languagesarrayyesTarget language codes for subtitle localization, for example ["fr", "ja"].

Structured output declared, but exposes no named fields.

No examples provided.

localize_subtitles ~304

Localize subtitles in-memory. Provide an SRT/ITT and/or a video (STT). Args: target_language_codes: Comma-separated codes (e.g. "fr,de,ja"). subtitle_path: Optional public HTTPS subtitle URL (hosted) or local path (stdio). video_path: Optional public HTTPS video URL (hosted) or local path (stdio) for STT. glossary_path: Optional public HTTPS glossary URL (hosted) or local path (stdio). source_language_code: Source language code. context: Optional localization context. formality: Optional formality override. output_dir: Local output directory (stdio). Hosted mode always returns subtitle download URLs.

NameTypeReqDescription
contextstring–Optional localization context.
formalitystring–Optional formality override.
glossary_pathstring–Optional public HTTPS glossary URL (hosted) or local path (stdio).
output_dirstring–Local output directory (stdio). Hosted mode always returns subtitle download URLs.
source_language_codestring–Source language code.
subtitle_pathstring–Optional public HTTPS subtitle URL (hosted) or local path (stdio).
target_language_codesstringyesComma-separated codes (e.g. "fr,de,ja").
video_pathstring–Optional public HTTPS video URL (hosted) or local path (stdio) for STT.
NameTypeReqDescription
resultstringyes–

No examples provided.

parse_audio_script ~63

Parse a script file (.txt, .docx, .pdf, .srt, .itt) instead of STT.

NameTypeReqDescription
file_pathstringyesInput file: local filesystem path in stdio, or an accessible public HTTPS URL on the hosted server.
NameTypeReqDescription
resultstringyes–

No examples provided.

parse_subtitle ~51

Parse an SRT/ITT file into timed cues (no storage).

NameTypeReqDescription
file_pathstringyesInput file: local filesystem path in stdio, or an accessible public HTTPS URL on the hosted server.
NameTypeReqDescription
resultstringyes–

No examples provided.

preview_voice ~134

Generate a short TTS preview. Hosted mode returns a download URL. Args: voice_id: Voice id from `list_voices`. output_path: Output filename hint (hosted) or WAV path (stdio). language_code: Optional locale. text: Optional preview line (max 200 chars).

NameTypeReqDescription
language_codestring–Optional locale.
output_pathstring–Output filename hint (hosted) or WAV path (stdio).
textstring–Optional preview line (max 200 chars).
voice_idstringyesVoice id from `list_voices`.
NameTypeReqDescription
resultstringyes–

No examples provided.

register_video ~50

Upload a source video for later remuxing. Returns video_id.

NameTypeReqDescription
file_pathstringyesInput file: local filesystem path in stdio, or an accessible public HTTPS URL on the hosted server.
NameTypeReqDescription
resultstringyes–

No examples provided.

remux_video ~139

Mux a WAV file onto a previously registered video. Args: video_id: Id from `register_video` or `transcribe_audio`. audio_path: Public HTTPS audio URL (hosted) or local file path (stdio). output_path: Output filename hint (hosted) or MP4 path (stdio).

NameTypeReqDescription
audio_pathstringyesPublic HTTPS audio URL (hosted) or local file path (stdio).
output_pathstring–Output filename hint (hosted) or MP4 path (stdio).
video_idstringyesId from `register_video` or `transcribe_audio`.
NameTypeReqDescription
resultstringyes–

No examples provided.

reorder_style_guides ~47

Save the order of workspace style guides using IDs from list_style_guides.

NameTypeReqDescription
guide_idsarrayyesNon-empty ordered list of unique style-guide IDs from list_style_guides.

Structured output declared, but exposes no named fields.

No examples provided.

search_translation_memory ~199

Search the translation memory for existing translations. Use this to check if translations already exist before creating new ones, or to find reference translations for consistency. Args: query: Text to search for in the translation memory. source_language_code: Source language code (default: "en"). target_language_code: Optional target language code to filter results. min_score: Minimum fuzzy match score (0-100). Default 0 returns all. limit: Maximum number of results (default 10).

NameTypeReqDescription
limitinteger–Maximum number of results (default 10).
min_scorenumber–Minimum fuzzy match score (0-100). Default 0 returns all.
querystringyesText to search for in the translation memory.
source_language_codestring–Source language code (default: "en").
target_language_codestring–Optional target language code to filter results.
NameTypeReqDescription
resultstringyes–

No examples provided.

submit_translation_feedback ~111

Save user feedback or an approval rating for a translation. This records feedback; add_translation_memory_entry separately saves an approved translation for reuse in future localization.

NameTypeReqDescription
approved––User approval state; saving approved memory requires explicit approval of the exact wording.
feedback––User feedback about this translation.
language––Target language for this operation, for example "French".
result––Translated text associated with this feedback.
source––Original text associated with this translation feedback.

Structured output declared, but exposes no named fields.

No examples provided.

synthesize_audio ~400

Generate billed localized TTS (and optional dubbed video). Hosted mode returns download URLs. Args: language: Target language name (e.g. "French"). language_code: Target language code (e.g. "fr"). voice_id: Voice id from `list_voices`. segments: JSON array of {text, start_ms, end_ms, original?} objects. output_path: Output filename hint (hosted) or WAV path (stdio). keep_same_length: Stretch/compress speech to source timings. keep_background_music: Mix transcribed music bed when stem_id is set. stem_id: Optional bed stem from `transcribe_audio`. source_duration_ms: Original duration. source_transcript: Optional original transcript. video_id: Optional id from transcribe/register to mux MP4. video_output_path: Optional path for dubbed MP4 when video_id is set.

NameTypeReqDescription
keep_background_musicboolean–Mix transcribed music bed when stem_id is set.
keep_same_lengthboolean–Stretch/compress speech to source timings.
languagestringyesTarget language name (e.g. "French").
language_codestringyesTarget language code (e.g. "fr").
output_pathstring–Output filename hint (hosted) or WAV path (stdio).
segmentsstringyesJSON array of {text, start_ms, end_ms, original?} objects.
source_duration_msinteger–Original duration.
source_transcriptstring–Optional original transcript.
stem_idstring–Optional bed stem from `transcribe_audio`.
video_idstring–Optional id from transcribe/register to mux MP4.
video_output_pathstring–Optional path for dubbed MP4 when video_id is set.
voice_idstringyesVoice id from `list_voices`.
NameTypeReqDescription
resultstringyes–

No examples provided.

synthesize_audio_advanced ~481

Synthesize multi-speaker audio/video with complete timing and review data. Billed operation. segments is a native array with text, start_ms, end_ms and optional original, speaker_id, voice_id, language_code and review fields returned by translation. speaker_voices maps each speaker_id to a preset or cloned voice_id. Pass stem_id to preserve background music and video_id to produce MP4. Outputs are local files (stdio) or expiring download URLs (hosted); no inline media blobs.

NameTypeReqDescription
document_translationboolean–Whether synthesis is for document-translation narration.
enterprise_long_formboolean–Request enterprise long-form processing only when allowed by get_audio_capabilities.
keep_background_musicboolean–Whether to retain the original background music for the dubbing workflow.
keep_same_lengthboolean–Whether synthesis should try to retain the original timing.
languagestringyesTarget language for this operation, for example "French".
language_codestringyesLanguage code, for example "en" or "fr". Leave empty to use the operation default.
output_pathstring–Output filename/path in stdio, or filename for the temporary hosted download. Use the matching file extension.
segmentsarrayyesNon-empty array of translated segments with text, start_ms, end_ms and optional original, speaker_id, voice_id, language_code and review fields.
source_duration_msinteger–Actual processed source duration in milliseconds, from transcription. Zero leaves it unspecified.
source_transcriptstring–Original transcript text for synthesis context; empty omits it.
speaker_voices––Optional mapping from transcript speaker_id to a preset or saved voice_id.
speech_islands––Optional speech timing ranges using integer start_ms and end_ms from detailed transcription.
stem_idstring–Background-music stem identifier returned by transcription; empty omits it.
video_idstring–Video identifier returned by registration/transcription; empty omits video assembly.
video_output_pathstring–Optional output MP4 filename/path; empty derives it from the audio output filename.
voice_idstringyesVoice identifier returned by list_voices or voice creation; reuse the exact identifier.

Structured output declared, but exposes no named fields.

No examples provided.

transcribe_audio ~224

Transcribe speech from an audio or video file (unbilled draft). Use the returned segments with `translate` (origin via text) then `synthesize_audio` to produce a dubbed track. Video uploads also return a video_id for muxing. Args: file_path: Public HTTPS URL (hosted) or local path (stdio) to audio (mp3, wav, m4a, …) or video (mp4, mov, …). source_language_code: Optional source language hint (e.g. "en"). keep_background_music: If true, split a music bed for later remix.

NameTypeReqDescription
file_pathstringyesPublic HTTPS URL (hosted) or local path (stdio) to audio (mp3, wav, m4a, …) or video (mp4, mov, …).
keep_background_musicboolean–If true, split a music bed for later remix.
source_language_codestring–Optional source language hint (e.g. "en").
NameTypeReqDescription
resultstringyes–

No examples provided.

transcribe_audio_detailed ~241

Transcribe audio/video with complete timed segments and speaker metadata. Unlike the compact transcribe_audio display, returns all segments with IDs, speaker IDs, speech islands, actual processed duration, video_id, and stem_id. Use for multi-speaker dubbing or long transcripts. File input is a local path (stdio) or public HTTPS URL (hosted). Draft step; check get_audio_capabilities before requesting long-form processing. speaker_count accepts 0 for automatic detection or 1–8 speakers.

NameTypeReqDescription
enterprise_long_formboolean–Request enterprise long-form processing only when allowed by get_audio_capabilities.
file_pathstringyesInput file: local filesystem path in stdio, or an accessible public HTTPS URL on the hosted server.
keep_background_musicboolean–Whether to retain the original background music for the dubbing workflow.
source_language_codestring–Source language code, for example "en"; empty omits the optional language hint/filter.
speaker_countinteger–Expected number of speakers: 0 for automatic detection, or 1–8.

Structured output declared, but exposes no named fields.

No examples provided.

translate ~431

Translate text using Nativ's AI localization engine. Uses the team's translation memory, style guides, and brand voice automatically. Returns the translation along with TM match info and rationale. Args: text: The text to translate. target_language: Full target language name (e.g. "French", "German", "Japanese"). target_language_code: Optional ISO language code (e.g. "fr", "de", "ja"). source_language: Source language name. Defaults to English. source_language_code: Source language code. Defaults to "en". context: Optional context to guide the translation (e.g. "marketing headline for Gen Z audience"). glossary: Optional inline glossary as CSV (e.g. "term,translation\nbrand,marque"). formality: Tone override — one of: very_informal, informal, neutral, formal, very_formal. max_characters: Optional strict character limit for the translation output. backtranslate: If true, also returns a back-translation to verify intent.

NameTypeReqDescription
backtranslateboolean–If true, also returns a back-translation to verify intent.
contextstring–Optional context to guide the translation (e.g. "marketing headline for Gen Z audience").
formalitystring–Tone override — one of: very_informal, informal, neutral, formal, very_formal.
glossarystring–Optional inline glossary as CSV (e.g. "term,translation\nbrand,marque").
max_charactersinteger–Optional strict character limit for the translation output.
source_languagestring–Source language name. Defaults to English.
source_language_codestring–Source language code. Defaults to "en".
target_languagestringyesFull target language name (e.g. "French", "German", "Japanese").
target_language_codestring–Optional ISO language code (e.g. "fr", "de", "ja").
textstringyesThe text to translate.
NameTypeReqDescription
resultstringyes–

No examples provided.

translate_batch ~267

Translate multiple texts to a single target language. Use for lists of strings, UI labels, i18n files, subtitle cues, and voiceover segments. Prefer one batch over separate translate calls. Texts are translated together using the team's TM and style guides. A failed or incomplete batch is a tool error; do not synthesize its output. Args: texts: List of texts to translate. target_language: Full target language name (e.g. "French"). target_language_code: Optional ISO language code. source_language: Source language name. Defaults to English. source_language_code: Source language code. Defaults to "en". context: Optional context to guide all translations. formality: Tone override for all translations.

NameTypeReqDescription
contextstring–Optional context to guide all translations.
formalitystring–Tone override for all translations.
source_languagestring–Source language name. Defaults to English.
source_language_codestring–Source language code. Defaults to "en".
target_languagestringyesFull target language name (e.g. "French").
target_language_codestring–Optional ISO language code.
textsarrayyesList of texts to translate.
NameTypeReqDescription
resultstringyes–

No examples provided.

translate_dialogue ~222

Localize speaker turns together with shared dialogue context. Each segment needs id, text, target_language, target_language_code and optional start_ms, end_ms, speaker_id from transcribe_audio_detailed. Returns timed translated turns with review details; different turns may target different languages. Does not synthesize speech.

NameTypeReqDescription
contextstring–Optional audience, purpose and surrounding context to guide localization.
formalitystring–Formality override: very_informal, informal, neutral, formal or very_formal. Empty uses workspace defaults.
segmentsarrayyes1–500 dialogue turns, each with id, text, target_language, target_language_code and optional start_ms, end_ms, speaker_id from detailed transcription.
source_languagestring–Source language name, for example "English".
source_language_codestring–Source language code, for example "en"; empty omits the optional language hint/filter.
speakers––Optional speaker metadata from detailed transcription, supplied alongside the dialogue turns.

Structured output declared, but exposes no named fields.

No examples provided.

update_language_custom_style ~68

Set saved per-language style instructions, or clear them with null. This persists workspace settings for the ID from list_language_settings.

NameTypeReqDescription
custom_style–yesCustom style instructions for this language mapping.
mapping_idintegeryesExact workspace language mapping ID returned by list_language_settings.

Structured output declared, but exposes no named fields.

No examples provided.

update_language_formality ~93

Change the saved formality for a mapping from list_language_settings. This persists workspace settings; use translate's formality argument for a one-off request instead.

NameTypeReqDescription
formalitystringyesFormality override: very_informal, informal, neutral, formal or very_formal. Empty uses workspace defaults.
mapping_idintegeryesExact workspace language mapping ID returned by list_language_settings.

Structured output declared, but exposes no named fields.

No examples provided.

update_style_guide ~94

Edit, enable or disable an existing workspace style guide.

NameTypeReqDescription
content––Style-guide instructions; omit/null on updates to leave them unchanged.
guide_idstringyesExact style-guide ID returned by list_style_guides.
is_enabled––Whether the style guide is enabled; omit/null on updates to leave it unchanged.
title––Style-guide title; omit/null on updates to leave it unchanged.

Structured output declared, but exposes no named fields.

No examples provided.

update_subtitle_review ~111

Save subtitle review edits: rows with row_index, translation, approved, rationale. Use row indices returned by get_subtitle_review. Export with export_subtitle(regenerate=true) after editing to apply the changes.

NameTypeReqDescription
storage_pathstringyesExact saved subtitle storage key returned by upload_subtitle or list_subtitles; not a local path or HTTPS URL.
updatesarrayyesReview edits with row_index from get_subtitle_review and translation, approved and/or rationale fields.

Structured output declared, but exposes no named fields.

No examples provided.

update_translation_memory_entry ~83

Edit an approved TM translation or enable/disable it for future translations.

NameTypeReqDescription
enabled––Whether this entry is enabled for future translations; null leaves it unchanged.
entry_idstringyesExact translation-memory entry ID returned by list_translation_memory_entries.
target_text––Translated wording for the memory entry; omit/null on updates to leave it unchanged.

Structured output declared, but exposes no named fields.

No examples provided.

upload_style_guide ~91

Create a workspace style guide from a .txt or .docx file. File input is a local path (stdio) or public HTTPS URL (hosted).

NameTypeReqDescription
file_pathstringyesInput file: local filesystem path in stdio, or an accessible public HTTPS URL on the hosted server.
titlestring–Style-guide title; omit/null on updates to leave it unchanged.

Structured output declared, but exposes no named fields.

No examples provided.

Install

How do I install the Nativ MCP server?

Nativ is a hosted endpoint at https://mcp.usenativ.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.usenativ.com

# add to Claude Code
claude mcp add --transport http nativ-technologies-nativ 'https://mcp.usenativ.com/mcp'
Common questions

What is the Nativ MCP server?

Nativ is an MCP server listed in the public MCP registry as io.github.Nativ-Technologies/nativ. Localize text, images, audio and subtitles with brand voice, memory and style guides. This page covers its hosted endpoint (https://mcp.usenativ.com/mcp).

Is the Nativ MCP server safe to use?

Nativ scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Nativ MCP server expose?

Nativ exposes 51 tools: translate, translate_batch, search_translation_memory, add_translation_memory_entry, get_languages, and 46 more. Their descriptions and schemas cost roughly 6,961 tokens of context every time the server is loaded.

Does the Nativ MCP server require authentication?

Yes. Nativ asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the Nativ MCP server still maintained?

Nativ is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Nativ MCP server?

VerifyMCP ran 13 checks on Nativ, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.