MCP Tools DirectoryAbout this integration
Local Kokoro-82M TTS MCP server that synthesizes and plays speech on your machine
- Transport
- stdio
- Authentication
- none
- Initial setup
- none
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.1.4
- Package
- mcp-kokoro-tts
- Last compatibility test
- Not independently tested
Connect your agent
mcp-kokoro-ttsPublisher documentation reviewed from the pinned README and pyproject manifest. First start downloads approximately 312 MB of model weights and provisions a spaCy model; Python 3.12, uv, and host playback tooling are prerequisites. Not installed, executed, downloaded, or independently security-audited.
Capabilities: Local text-to-speech synthesis, Voice discovery and selection, Local WAV playback
Connected profiles
Additional details
io.github.mrfqcentic/mcp-kokoro-tts
Source ↗ · Checked 2026-09-170.1.4
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17mcp-kokoro-tts
Source ↗ · Checked 2026-09-190.1.4
Source ↗ · Checked 2026-09-19The publisher documents automatic model and language-model provisioning on the first server start; this review did not start the server, download models, synthesize speech, or test playback.
Source ↗ · Checked 2026-09-19The publisher explicitly documents local synthesis with no API keys; an optional Hugging Face token can accelerate model downloads but is not required for the documented connection.
Source ↗ · Checked 2026-09-19The documented MCP client configuration launches mcp-kokoro-tts locally with uvx.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19