Home / MCP registry index / com.nicevois/rvc-training
NiceVois
com.nicevois/rvc-training in the official MCP registry.
Endpoint https://nicevois.com/api/mcp.
The registry describes it as: Free stem, lead/backing vocal, noise and reverb splitting, no account. Train and use RVC voices.
We read its 16 tools on 2026-10-21. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
get_training_requirements get_training_account quote_training create_training_job start_training get_training_job list_training_jobs get_conversion_requirements list_voice_models create_voice_model_import create_voice_conversion get_voice_conversion download_voice_conversion_output list_free_audio_tools create_free_audio_job get_free_audio_job
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/com-nicevois-rvc-training)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.