African Speech Corpora Quality Audit runs on your own machine — the client starts it, so there is no endpoint to ping. 105 installs a week from pypi. Last commit 27 Aug 2026.
Read-only, provenance-aware selection of Wolof speech corpora by measured quality.
Today is the operative word: we check African Speech Corpora Quality Audit every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add african-speech-corpora -- uvx african-speech-mcp
{
"mcpServers": {
"african-speech-corpora": {
"args": [
"african-speech-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.african-speech-corpora]
command = "uvx"
args = ["african-speech-mcp"]
{
"mcpServers": {
"african-speech-corpora": {
"args": [
"african-speech-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"african-speech-corpora": {
"args": [
"african-speech-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
ASM_CATALOG_PATH (Optional path to a custom corpus catalog JSON file.), ASM_AUDIT_LOG_PATH (Optional path receiving one JSON audit line per tool call.), ASM_HF_TOKEN (Optional Hugging Face token, only needed for gated datasets.), ASM_VALIDATION_LOCK_PATH (Optional path to a local schema-validation lock bound to the catalog hash.).
The author declared them in the registry entry; get the values from the project itself.
Read-only access to an append-only corpus of provenance-bearing coordination records.
MCP server: x402-paid & free tools for AI agents — provenance, quality scoring, action audit.
OAuth-protected, read-only-by-default MCP server for provenance-labeled QuillCaddie project memory.
Read-only pre-sign evidence for onchain agents: route quality, MEV exposure, clear/caution verdict.
Read-only BSB and WEB Scripture evidence with provenance, context, comparison, and search.
Search launched software (SaaS, AI tools, MCP servers) by measured production-readiness.
Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
Read-only validation of rights-aware production metadata manifests for MCP-compatible clients.
Answers built from our own checks of this server.