Mcp Voice — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Mcp Voice (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
An MCP server that lets Claude generate, rewrite, de-AI, and transform written text so it reads as a specific human voice — primarily the operator's own, extensible to other authorized voices. Not for impersonating arbitrary third parties.
Early build. Specs (research-backed, decisions resolved) live in the system repo:
voice-mcp-research.md — verified research + the three architecture callsvoice-mcp-spec-00-benchmark-spike.md — calibration spike (prerequisite)voice-mcp-spec-01-ingestion.md — corpus ingestion ← building nowvoice-mcp-spec-02-storage.md — voice. schema + dual embeddingsvoice-mcp-spec-03-eval-harness.md — stylometric + detector gates (Python sidecar)voice-mcp-spec-04-voice-model.md — the generation enginevoice-mcp-spec-05-de-ai.md — tell registry + surgical remediationvoice-mcp-spec-06-mcp-design.md — the 7-tool MCP surfacevoice. schema.Bun + TypeScript, Biome, knip, bun test.
bun install
bun test
bun run quality # biome ci + knip + tsc~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.