MCP Tools DirectoryAbout this integration
Local MCP voice coach with English pronunciation, grammar, and fluency feedback.
- Transport
- stdio
- Authentication
- none
- Initial setup
- none
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.3.0
- Package
- mcp-server-pronunciation
- Last compatibility test
- Not independently tested
Connect your agent
mcp-server-pronunciationPublisher documentation and executable manifest were reviewed; package, model, microphone, audio, and optional model downloads were not executed. Feedback is publisher-described as an experimental coaching signal, not a clinical, employment, or standardized assessment.
Capabilities: Capture and transcribe local microphone audio, Provide pronunciation, grammar, fluency, and prosody coaching, Run focused sentence drills and retries, Track visible background voice-capture sessions
Connected profiles
Additional details
io.github.JuhongPark/pronunciation
Source ↗ · Checked 2026-09-170.3.0
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17mcp-server-pronunciation
Source ↗ · Checked 2026-09-190.3.0
Source ↗ · Checked 2026-09-19The stdio server is launched by uvx and preloads the local Whisper model in the background after the MCP handshake; preload can be disabled for discovery-only environments.
Source ↗ · Checked 2026-09-19No account credential is documented: speech processing and audio storage are local, with no external service calls other than one-time model-weight downloads.
Source ↗ · Checked 2026-09-19MCP clients launch uvx mcp-server-pronunciation over local stdio; microphone access and platform audio dependencies are prerequisites.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19