C
Emerging
74/100
20 hours ago

commendation

MCP server that recommends new songs from YouTube Music, ensuring no song is already liked or in any playlist, using multiple independent signals for explainable rankings.

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

umsachde · Claimed

Source: Glama

⚡ Upgrade to Live Monitored

Connect your repo and M8ven re-verifies it on the push itself. Without it we re-check verified listings about once a day, so a fix can sit unseen. Read-only, one click, revoke anytime. What we access →

Install from

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
Are you the publisher? Confirm or correct these findings.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configRECOM_CACHE_PATH~/.recom/library_cache.json Where the cached set lives (~22 KB).
configRECOM_CACHE_TTLto and a later call can recommend a song you just saved.
configRECOM_PROVIDER2. Point re-com at it via RECOM_YTMUSIC_MCP_COMMAND (its interpreter) and RECOM_YTMUSIC_MCP_ARGS (its server.py path). =youtube is the default, so it doesn't need to be set explicitly.
configRECOM_JUDGE_MODELclaude-opus-5 Model for lyric-based labelling.
configRECOM_JUDGE_EFFORTlow Effort level for that labelling.
configRECOM_JUDGE_BATCH12 Songs per labelling request.
configRECOM_SPOTIFY_MCP_COMMAND2. Register a second, separate re-com instance with RECOM_PROVIDER=spotify and / RECOM_SPOTIFY_MCP_ARGS pointing at it:
configRECOM_SPOTIFY_MCP_ARGS2. Register a second, separate re-com instance with RECOM_PROVIDER=spotify and RECOM_SPOTIFY_MCP_COMMAND / pointing at it:
configRECOM_DB_PATH~/.recom/store.db Mood index, labels, history, feedback.
configRECOM_YTMUSIC_MCP_COMMAND2. Point re-com at it via (its interpreter) and RECOM_YTMUSIC_MCP_ARGS (its server.py path). RECOM_PROVIDER=youtube is the default, so it doesn't need to be set explicitly.
configRECOM_YTMUSIC_MCP_ARGS2. Point re-com at it via RECOM_YTMUSIC_MCP_COMMAND (its interpreter) and (its server.py path). RECOM_PROVIDER=youtube is the default, so it doesn't need to be set explicitly.
configRECOM_AUTH_PATH
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

10/10 tools missing one or more hints — recommend_from_song (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); recommend_from_playlist (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); songs_by_artist (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +7 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Secrets not written to files

1 secret value written to files

Avoid persisting secrets to disk. Keep them in memory or your secret manager.

Secrets not logged

12 secret values sent to console.log

Redact or omit secret values from log output.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/umsachde-commendation-19gofo)](https://m8ven.ai/mcp/umsachde-commendation-19gofo)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 6491af9f6c7627b0524e81d872f8944528356008
code hash: 898c0ebc0fa20c1dbccdee72fd6c3c3e88f17546a3a2f45cccd0ef7aa6cb59b7
verified: 8/21/2026, 9:57:52 AM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client