African Speech Corpora Quality Audit for VS Code
io.github.papasega/african-speech-corpora
Read-only, provenance-aware selection of Wolof speech corpora by measured quality.
client:VS Code
transport:stdio
runtime:pypi
Install African Speech Corpora Quality Audit in VS Code
.vscode/mcp.json
{
"inputs": [
{
"type": "promptString",
"id": "asm-catalog-path",
"description": "ASM_CATALOG_PATH",
"password": true
},
{
"type": "promptString",
"id": "asm-audit-log-path",
"description": "ASM_AUDIT_LOG_PATH",
"password": true
},
{
"type": "promptString",
"id": "asm-hf-token",
"description": "ASM_HF_TOKEN",
"password": true
},
{
"type": "promptString",
"id": "asm-validation-lock-path",
"description": "ASM_VALIDATION_LOCK_PATH",
"password": true
}
],
"servers": {
"african-speech-corpora": {
"type": "stdio",
"command": "uvx",
"args": [
"african-speech-mcp"
],
"env": {
"ASM_CATALOG_PATH": "${input:asm-catalog-path}",
"ASM_AUDIT_LOG_PATH": "${input:asm-audit-log-path}",
"ASM_HF_TOKEN": "${input:asm-hf-token}",
"ASM_VALIDATION_LOCK_PATH": "${input:asm-validation-lock-path}"
}
}
}
}
VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs