Vocaless MCP server
io.github.ajselzilic/vocaless·v0.1.3Remove vocals from local audio files and transpose instrumentals through Vocaless.
24 downloads/wk
Reviews
Write oneNobody has reviewed Vocaless yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Vocaless tools (3)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
check_balanceReport the Vocaless credit balance and storage usage. Call this before separating several songs, so a shortfall is known up front instead of failing partway through, and whenever a call fails with INSUFFICIENT_CREDITS or STORAGE_LIMIT.
get_stemsFetch download URLs for a separated song, optionally transposed or time-stretched. Call this after separate_vocals to collect the result, and call it again to change key or tempo. Transposing and time-stretching are free. If separation is still running this reports the status instead, so poll it every few seconds until the URLs come back.
separate_vocalsSplit an audio file on this machine into a clean instrumental and an isolated vocal track. Call this when the user wants a backing track, a karaoke version, an acapella, or the vocals removed from a song they have on disk. Charges credits per minute of audio; call check_balance for the current rate. Returns a song_id immediately; separation finishes in the background, so call get_stems with that i
Public scan report
scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it
- Code scan3 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenanceno repository listed3/15
- Maintainer identityno repository or website to verify2/10
Findings (1)
- lowNo source repository listed
maint.no-repo
How Vocaless compares
Against every graded Media MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 55/100
- higher than 10% of 1,336 Media servers
- Tools
- 3
- the typical Media server has 6
- Tools that change things
- 0%
- typical: 3%. Fewer write tools means less an agent can break
- Downloads a week
- 24
- more than 10% of 372 Media servers with a package
What its tools let an agent do: 3 read
Install Vocaless in Claude Code, Cursor or VS Code
Runs npx -y @vocaless/mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add vocaless -- npx -y @vocaless/mcp
Vocaless: common questions
- Is Vocaless MCP server safe?
- With care: it is graded C, so read the findings first (55/100). Read the Vocaless safety report
- How do I install Vocaless?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Vocaless need an API key?
- Yes. The registry entry asks for
VOCALESS_API_KEY. - Is Vocaless maintained?
- The latest release is v0.1.3.
- What can I use instead of Vocaless?
- Servers from other publishers that do the same job: anymd MCP server, Remove AI Watermarks MCP server and FunASR MCP server.
- How does Vocaless compare with other Media MCP servers?
- safety score 55/100 (higher than 10% of 1,336 Media servers); tools 3 (the typical Media server has 6); tools that change things 0% (typical: 3%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Vocaless
Same job from other publishers: the closest match first, then the best rated.
- anymdAny file → clean Markdown for AI agents: PDF, Office, EPUB, HTML, images, audio/video. Local MCP.not reviewedEstablishedA
- Remove AI WatermarksIdentify and remove AI watermarks and provenance metadata from your own images and video.not reviewedWidely usedA
- FunASRTranscribe local audio with FunASR and SenseVoice using private, on-device inference.not reviewedEstablishedA
- FFmpegTrim, convert, resize, compress, and remix audio and video.not reviewedEstablishedA
- AudioEdit, analyze and convert audio: loudness, spec checks, denoise, EQ, cuts, BPM, key. No ffmpeg.not reviewedEstablishedA