YouTube Dubbing MCP
OCI · DOCKER.IO/MIRAGEA/YOUTUBE-DUBBING-MCP
AI dubbing for YouTube videos: one cloned voice per speaker, synced SRT, YouTube audio tracks.
Available components
Last scanned (23 hours ago)
Scores higher than 35% of OCI servers
Category Design and Media
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 10 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability64
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1404 tokens (~117/item across 12 items; 12 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 Management37
- Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- 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
- We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Checks we ran (12)
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (4)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Malware scan in Supply Chain Security (scores 0 for this)No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
- Known CVEs in Supply Chain Security (scores 0 for this)Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- Install scripts in Supply Chain Security (scores 0 for this)Install-script risk not yet assessed.
- Dependency health in Supply Chain Security (scores 0 for this)Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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.
- 21 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
- 19 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.
- 17 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.
- 15 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 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Nov 26 34
First indexed and scored.
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 · Analysed oci/docker.io/miragea/youtube-dubbing-mcp@0.1.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
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 →
dubbing_assign_speakers ~88
Set who speaks each segment. `assignments` maps a segment id ('7'), an inclusive range ('7-12') or '*' (all) to a speaker name, e.g. {'1-4': 'Anna', '5': 'Ben'}. Use when captions had no speaker markers.
| Name | Type | Req | Description |
|---|---|---|---|
| assignments | object | yes | – |
| project_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
dubbing_check_setup ~58
Check that dubbing will work: API key set (value hidden), voice engine reachable, its voice models and limits, ffmpeg and yt-dlp available, and where projects are saved. Read-only; creates no job. Call first.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
dubbing_export_youtube_package ~95
Write the YouTube upload package: one folder per language with audio.m4a (the dub track, video length), captions.srt, title.txt and description.txt, plus UPLOAD-TO-YOUTUBE.md with the YouTube Studio > Languages steps and a Studio link. The YouTube API cannot upload audio tracks, so the user uploads them.
| Name | Type | Req | Description |
|---|---|---|---|
| languages | – | – | – |
| project_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
dubbing_extract_voice_samples ~110
Cut a clean 4-14 second voice sample for each speaker from the source audio, with its transcript. With share=true each sample is uploaded to a temporary public file host (uguu.se, deleted after a few hours) so the voice engine can clone it, and the speaker's voice is set automatically. Ask the user before sharing someone's voice. With share=false the samples stay local.
| Name | Type | Req | Description |
|---|---|---|---|
| project_id | string | yes | – |
| share | boolean | – | – |
| speakers | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
dubbing_get_segments ~98
Read a project's transcript in pages: id, speaker, start, slot_seconds and text. With target_language, each line also gets target_chars and max_chars, the length that fits its time slot when spoken in that language, plus any translation already saved. Use it to review speakers and to translate.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| offset | integer | – | – |
| project_id | string | yes | – |
| target_language | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
dubbing_list_projects ~22
List dubbing projects saved on this machine, newest first.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
dubbing_list_voices ~54
List the voices saved in the user's Miragea account (actor_id, name, language) to use with dubbing_set_voice. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| offset | integer | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
dubbing_project_status ~36
Show a project's state: speakers and their voices, languages translated and rendered, output paths.
| Name | Type | Req | Description |
|---|---|---|---|
| project_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
dubbing_render ~157
Voice every translated line with its speaker's voice, then build the dubbed audio track at the exact video length (each line starts with the original; lines are sped up only when needed, max_speedup 1.0-1.5), the translated SRT, and a preview MP4 when the video was downloaded. Optional background: a music/effects file mixed under the voices. Re-running reuses finished lines and resumes pending ones.
| Name | Type | Req | Description |
|---|---|---|---|
| audio_format | string | – | – |
| background_file | – | – | – |
| background_volume | number | – | – |
| language | string | yes | – |
| max_speedup | number | – | – |
| model | – | – | – |
| preview_video | boolean | – | – |
| project_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
dubbing_set_translation ~111
Save translated lines for a target language as {segment_id: text} (all at once or in batches; later calls update only the ids given), plus an optional localized YouTube title and description. Returns a fit check: lines that are too long for their time slot, and ids still missing.
| Name | Type | Req | Description |
|---|---|---|---|
| description | – | – | – |
| language | string | yes | – |
| max_speedup | number | – | – |
| project_id | string | yes | – |
| title | – | – | – |
| translations | object | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
dubbing_set_voice ~119
Choose the voice for one speaker: a saved voice (actor_id from dubbing_list_voices) or a voice to clone from a public reference_audio_url (6-15 s of clean speech) with its exact reference_text. Optional model ('expressive' or 'standard') and speed (0.25-4).
| Name | Type | Req | Description |
|---|---|---|---|
| actor_id | – | – | – |
| model | – | – | – |
| project_id | string | yes | – |
| reference_audio_url | – | – | – |
| reference_text | – | – | – |
| speaker | string | yes | – |
| speed | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
dubbing_start_project ~161
Start a dubbing project from a YouTube URL, a local video/audio file, or an SRT/VTT caption file. Downloads the audio (and optionally the video for a preview), takes the transcript from YouTube captions when available or transcribes the speech, merges caption fragments into sentences and labels speakers from caption markers (Name:, [Name], >>) or, without markers, by voice pitch (set num_speakers if known). Returns project_id, duration, speakers and segment count.
| Name | Type | Req | Description |
|---|---|---|---|
| captions_file | – | – | – |
| download_video | boolean | – | – |
| num_speakers | – | – | – |
| prefer_captions | boolean | – | – |
| project_name | – | – | – |
| source | string | yes | – |
| source_language | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the YouTube Dubbing MCP server?
YouTube Dubbing MCP runs locally as a container image, launched with docker run --rm -i -e MIRAGEA_API_KEY docker.io/miragea/youtube-dubbing-mcp:0.1.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · docker.io/miragea/youtube-dubbing-mcp
claude mcp add rty2345rr-youtube-dubbing-mcp -- docker run --rm -i -e MIRAGEA_API_KEY docker.io/miragea/youtube-dubbing-mcp:0.1.0
This image reads MIRAGEA_API_KEY. Set it in your client's env block for this server; docker run -e passes it through to the container.
What is the YouTube Dubbing MCP server?
YouTube Dubbing MCP is listed in the public MCP registry as io.github.RTY2345RR/youtube-dubbing-mcp. AI dubbing for YouTube videos: one cloned voice per speaker, synced SRT, YouTube audio tracks. This page covers its container image (docker.io/miragea/youtube-dubbing-mcp).
Is the YouTube Dubbing MCP server safe to use?
YouTube Dubbing MCP scores 39 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 YouTube Dubbing MCP server expose?
YouTube Dubbing MCP exposes 12 tools: dubbing_check_setup, dubbing_list_voices, dubbing_start_project, dubbing_get_segments, dubbing_assign_speakers, and 7 more. Their descriptions and schemas cost roughly 1,109 tokens of context every time the server is loaded.
Is the YouTube Dubbing MCP server still maintained?
YouTube Dubbing MCP 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 YouTube Dubbing MCP server?
VerifyMCP ran 12 checks on YouTube Dubbing MCP, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about YouTube Dubbing MCP: Malware scan, Known CVEs, Install scripts and Dependency health. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a container image, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.