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.

Wubble

REMOTE · MCP.WUBBLE.AI · SCANNED SEP 24

Create, inspect, and manage Wubble music, speech, voice, and sound-effect requests through MCP.

Available components

0 this week 78 Trust /100

Recent critical change

Authorization (7 Aug 2026). See the changelog before you install this server.

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 Security57
Transport & Reachability100
Schema Quality & AI Usability74
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 2493 tokens (~73/item across 34 items; 33 tools + 1 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage99
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 96% of tool parameters carry a description.Partial
  • 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 33 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 34 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
  • Supports UI / widget rendering.Pass
Install

How do I install the Wubble MCP server?

Wubble is a hosted endpoint at https://mcp.wubble.ai/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.wubble.ai

# add to Claude Code
claude mcp add --transport http ai-wubble-audio 'https://mcp.wubble.ai/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "ai-wubble-audio": {
      "url": "https://mcp.wubble.ai/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "ai-wubble-audio": {
      "type": "http",
      "url": "https://mcp.wubble.ai/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.ai-wubble-audio]
url = "https://mcp.wubble.ai/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-wubble-audio": {
      "type": "remote",
      "url": "https://mcp.wubble.ai/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add ai-wubble-audio --url 'https://mcp.wubble.ai/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  ai-wubble-audio:
    url: "https://mcp.wubble.ai/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "ai-wubble-audio": {
      "Transport": "http",
      "Url": "https://mcp.wubble.ai/mcp"
    }
  }
}
# add to Vellum
assistant mcp add ai-wubble-audio -t streamable-http -u 'https://mcp.wubble.ai/mcp'
// mcp.json
{
  "mcpServers": {
    "ai-wubble-audio": {
      "type": "http",
      "url": "https://mcp.wubble.ai/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

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.

  • 26 Aug 26 78
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 0
    • Stability: 0.97 → pass security
  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 7 Aug 26 0
    • Authorization: unverified → fail ▼ critical
  • 31 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 26 Jul 26 0

    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 24 Sept 2026 · Probed https://mcp.wubble.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.wubble.ai CN=Amazon RSA 2048 M01,O=Amazon,C=US 27 Apr 2026 10 Nov 2026 RSA 2048 SHA256-RSA 16bbeba780a844752e339b2affc1498
SANs: *.wubble.ai
CN=Amazon RSA 2048 M01,O=Amazon,C=US (CA) CN=Amazon Root CA 1,O=Amazon,C=US 23 Aug 2022 23 Aug 2030 RSA 2048 SHA256-RSA 77312380b9d6688a33b1ed9bf9ccda68e0e0f
CN=Amazon Root CA 1,O=Amazon,C=US (CA) CN=Starfield Services Root Certificate Authority - G2,O=Starfield Technologies\, Inc.,L=Scottsdale,ST=Arizona,C=US 25 May 2015 31 Dec 2037 RSA 2048 SHA256-RSA 67f944a2a27cdf3fac2ae2b01f908eeb9c4c6

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.wubble.ai. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
ai. present 3799 8 Verified
wubble.ai. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.wubble.ai/mcp Verified 200
http (plaintext) http://mcp.wubble.ai/mcp HTTPS enforced
MCP tools · 33 exposed · ~2,477 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
wubble_analyze_lyrics ~41

Analyze Wubble lyrics. Consumes Wubble requests or credits.

NameTypeReqDescription
upload_audio_idstringyesUploaded Wubble audio ID to analyze.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_change_voice ~86

Change Wubble voice. Consumes Wubble requests or credits.

NameTypeReqDescription
file_formatstring–Optional file format.
model_idstring–Optional model ID.
output_formatstring–Optional output format.
source_urlstringyesHTTPS URL for MCP to fetch and convert.
target_voice_idstringyesTarget Wubble voice ID.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_create_instrumental_and_wait ~78

Create Wubble instrumental and wait. Consumes Wubble requests or credits.

NameTypeReqDescription
poll_interval_secondsnumber–Seconds between status checks. Max 10.
promptstringyesDescription of the instrumental track to generate.
timeout_secondsnumber–Maximum seconds to wait for completion. Max 45.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_create_podcast ~62

Create Wubble podcast. Consumes Wubble requests or credits.

NameTypeReqDescription
background_musicboolean–Whether to include background music.
conversationsarray––
promptstringyesPodcast topic or direction.
voicesarray––
NameTypeReqDescription
dataobject–Wubble developer-service response data.
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_create_song_and_wait ~89

Create Wubble song and wait. Consumes Wubble requests or credits.

NameTypeReqDescription
lyricsstring–Optional lyrics to use for the song.
poll_interval_secondsnumber–Seconds between status checks. Max 10.
promptstringyesDescription of the song to generate.
timeout_secondsnumber–Maximum seconds to wait for completion. Max 45.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_create_sound_effect_and_wait ~135

Create Wubble sound effect and wait. Consumes Wubble requests or credits.

NameTypeReqDescription
duration_secondsnumber–Optional duration from 0.5 to 30 seconds.
loopboolean–Whether the sound effect should loop.
output_formatstring–Optional output format.
poll_interval_secondsnumber–Seconds between status checks. Max 10.
prompt_influencenumber–Optional prompt influence from 0 to 1.
textstringyesSound effect description.
timeout_secondsnumber–Maximum seconds to wait for completion. Max 45.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_create_voiceover_and_wait ~158

Create Wubble voiceover and wait. Consumes Wubble requests or credits.

NameTypeReqDescription
language_codestring–Optional language code.
model_idstring–Optional model ID.
output_formatstring–Optional output format. Use mp3_44100_128 for MP3 audio; shorthand mp3 is accepted and normalized.
poll_interval_secondsnumber–Seconds between status checks. Max 10.
textstringyesText to synthesize into a finished voiceover.
timeout_secondsnumber–Maximum seconds to wait for completion. Max 45.
voice_idstring–Optional Wubble voice ID.
voice_settingsobject–Optional voice settings.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_describe_audio ~51

Describe Wubble audio. Consumes Wubble requests or credits.

NameTypeReqDescription
modelstring–Optional model.
urlstringyesWubble-owned or user-provided audio URL to describe.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_dub_audio ~196

Dub Wubble audio. Consumes Wubble requests or credits.

NameTypeReqDescription
disable_voice_cloningboolean–Whether to disable voice cloning.
drop_background_audioboolean–Whether to drop background audio.
dubbing_studioboolean–Whether to enable dubbing studio.
end_timenumber–Optional end time.
highest_resolutionboolean–Whether to request highest resolution.
namestring–Optional dubbing job name.
num_speakersnumber–Optional number of speakers.
source_langstring–Optional source language code.
source_urlstringyesHTTPS URL for MCP to fetch and dub.
start_timenumber–Optional start time.
target_langstringyesTarget language code.
use_profanity_filterboolean–Whether to use profanity filter.
watermarkboolean–Whether to watermark output.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_edit_track ~101

Edit Wubble track. Consumes Wubble requests or credits.

NameTypeReqDescription
edit_endnumberyesEdit region end in milliseconds.
edit_startnumberyesEdit region start in milliseconds.
lyricsstring–Optional replacement lyrics.
source_duration_msnumber–Optional source duration in milliseconds.
track_idstring–Caller-owned track/song request ID.
upload_audio_idstring–Uploaded Wubble audio ID.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_extend_lyrics ~47

Extend Wubble lyrics. Consumes Wubble requests or credits.

NameTypeReqDescription
lyricsstringyesExisting lyrics to extend.
promptstring–Optional direction for the extension.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_extend_song ~92

Extend Wubble song. Consumes Wubble requests or credits.

NameTypeReqDescription
extend_atnumberyesExtension position in milliseconds.
extend_typestring–Where to extend the song.
lyricsstringyesLyrics for the extension.
modelstring–Optional model.
promptstring–Optional extension prompt.
song_idstringyesCaller-owned completed song request ID.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_generate_instrumental ~39

Generate Wubble instrumental. Consumes Wubble requests or credits.

NameTypeReqDescription
promptstringyesDescription of the instrumental track to generate.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_generate_lyrics ~47

Generate Wubble lyrics. Consumes Wubble requests or credits.

NameTypeReqDescription
promptstringyesDescription of the lyrics to generate.
stylestring–Optional lyric style.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_generate_song ~50

Generate Wubble song. Consumes Wubble requests or credits.

NameTypeReqDescription
lyricsstring–Optional lyrics to use for the song.
promptstringyesDescription of the song to generate.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_generate_sound_effect ~96

Generate Wubble sound effect. Consumes Wubble requests or credits.

NameTypeReqDescription
duration_secondsnumber–Optional duration from 0.5 to 30 seconds.
loopboolean–Whether the sound effect should loop.
output_formatstring–Optional output format.
prompt_influencenumber–Optional prompt influence from 0 to 1.
textstringyesSound effect description.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_generate_track ~117

Generate Wubble track. Consumes Wubble requests or credits.

NameTypeReqDescription
generate_endnumber–End time in milliseconds.
generate_startnumber–Start time in milliseconds.
generate_typestringyesTrack type to generate.
lyricsstring–Optional lyrics.
promptstring–Optional generation prompt.
song_idstring–Caller-owned completed song request ID.
upload_audio_idstring–Uploaded Wubble audio ID.
vocal_genderstring–Optional vocal gender.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_get_credits ~25

Get Wubble credits. Reads information from the connected Wubble account.

Input schema present but exposes no named parameters.

NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_get_dubbing_transcript ~63

Get Wubble dubbing transcript. Reads information from the connected Wubble account.

NameTypeReqDescription
dubbingIdstringyesDubbing provider/request ID.
formatstringyesTranscript format.
language_codestringyesTranscript language code.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_get_request_status ~40

Get Wubble request status. Reads information from the connected Wubble account.

NameTypeReqDescription
requestIdstringyesWubble request ID to inspect.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_get_speech_status ~40

Get Wubble speech status. Reads information from the connected Wubble account.

NameTypeReqDescription
requestIdstringyesSpeech request ID to inspect.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_get_started ~25

Get started with Wubble. Reads information from the connected Wubble account.

Input schema present but exposes no named parameters.

NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_get_usage ~24

Get Wubble usage. Reads information from the connected Wubble account.

Input schema present but exposes no named parameters.

NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_isolate_voice ~54

Isolate Wubble voice. Consumes Wubble requests or credits.

NameTypeReqDescription
file_formatstring–Optional file format.
source_urlstringyesHTTPS URL for MCP to fetch and isolate vocals from.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_list_voices ~25

List Wubble voices. Reads information from the connected Wubble account.

Input schema present but exposes no named parameters.

NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_remix_song ~84

Remix Wubble song. Consumes Wubble requests or credits.

NameTypeReqDescription
lyricsstringyesLyrics for the remix.
nnumber–Optional number of variations.
promptstring–Optional remix prompt.
song_idstring–Caller-owned completed song request ID.
upload_audio_idstring–Uploaded Wubble audio ID.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_separate_stems ~53

Separate Wubble stems. Consumes Wubble requests or credits.

NameTypeReqDescription
modelstring–Optional model.
urlstringyesWubble-owned or user-provided audio URL for stem separation.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_speech_to_text ~114

Transcribe Wubble speech. Consumes Wubble requests or credits.

NameTypeReqDescription
detect_speaker_rolesboolean–Whether to detect speaker roles.
diarizeboolean–Whether to diarize speakers.
keytermsarray––
language_codestring–Optional language code.
model_idstring–Optional model ID.
source_urlstringyesHTTPS URL for MCP to fetch and transcribe.
timestamps_granularitystring–Timestamp granularity.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_text_to_dialog ~107

Generate Wubble dialog. Consumes Wubble requests or credits.

NameTypeReqDescription
apply_text_normalizationstring–Text normalization mode.
inputsarrayyes–
language_codestring–Optional language code.
model_idstring–Optional model ID.
output_formatstring–Optional output format.
pronunciation_dictionary_locatorsarray––
seednumber–Optional deterministic seed.
settingsobject–Optional dialog settings.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_text_to_speech ~114

Generate Wubble speech. Consumes Wubble requests or credits.

NameTypeReqDescription
language_codestring–Optional language code.
model_idstring–Optional model ID.
output_formatstring–Optional output format. Use mp3_44100_128 for MP3 audio; shorthand mp3 is accepted and normalized.
textstringyesText to synthesize.
voice_idstring–Optional Wubble voice ID.
voice_settingsobject–Optional voice settings.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_upload_audio ~77

Upload Wubble audio. Consumes Wubble requests or credits.

NameTypeReqDescription
content_typestring–Optional media content type.
filenamestring–Optional filename for the uploaded audio.
purposestring–Optional upload purpose.
source_urlstringyesHTTPS URL for MCP to fetch and upload to Wubble.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_upload_vocal ~69

Upload Wubble vocal. Consumes Wubble requests or credits.

NameTypeReqDescription
content_typestring–Optional media content type.
filenamestring–Optional filename for the uploaded vocal.
source_urlstringyesHTTPS URL for MCP to fetch and upload as a vocal reference.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

wubble_wait_for_request ~78

Wait for Wubble request. Reads information from the connected Wubble account.

NameTypeReqDescription
poll_interval_secondsnumber–Seconds between status checks. Max 10.
requestIdstringyesWubble request ID to wait for.
timeout_secondsnumber–Maximum seconds to wait in this tool call. Max 45.
NameTypeReqDescription
dataobject––
errorobject–Developer-service error envelope when the call fails.
successbooleanyesWhether the developer-service request succeeded.

No examples provided.

Common questions

What is the Wubble MCP server?

Wubble is an MCP server listed in the public MCP registry as ai.wubble/audio. Create, inspect, and manage Wubble music, speech, voice, and sound-effect requests through MCP. This page covers its hosted endpoint (https://mcp.wubble.ai/mcp).

Is the Wubble MCP server safe to use?

Wubble scores 78 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 Wubble MCP server expose?

Wubble exposes 33 tools: wubble_get_started, wubble_get_credits, wubble_get_usage, wubble_get_request_status, wubble_wait_for_request, and 28 more. Their descriptions and schemas cost roughly 2,477 tokens of context every time the server is loaded.

Does the Wubble MCP server require authentication?

No. We connected to Wubble without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Wubble MCP server still maintained?

Wubble is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.