Koskamo

mcp-server-pronunciation

A local MCP voice coach that enables voice conversation with an assistant while providing real-time feedback on English pronunciation, grammar, and fluency. It runs entirely on-device using faster-whisper for transcription and supports phoneme-level drills, learner-profile hints, and cross-platform compatibility.

Package and access

Local package with source-attributed installation metadata. Koskamo does not execute packages during review.

mcp-server-pronunciation logo, by JuhongParkCommunity listingLocal stdioSource reviewed; not executedPublished by JuhongPark
Vendor documentation

Checks and signals

Each line is separate evidence, not a trust score.

  • Popularity 3 GitHub stars

What you can do with it

  • Casual voice chat with light coaching
  • Phoneme-level drill feedback for specific sentences
  • Grammar and fluency analysis during conversation
  • Local-only speech transcription and feedback

Source and maintenance

Community listingRegistry 0.3.0MIT
Last repository push
Latest release
v0.3.0
Maintenance checked

Packages and installation

Source-provided package data. Koskamo has not executed or live-probed this package.

mcp-server-pronunciation 0.3.0

pypiuvx
mcp-server-pronunciation package definition
{
  "version": "0.3.0",
  "transport": "stdio",
  "identifier": "mcp-server-pronunciation",
  "runtimeHint": "uvx",
  "registryType": "pypi",
  "registryBaseUrl": "https://pypi.org",
  "environmentVariables": [
    {
      "name": "MCP_PRONUNCIATION_MODEL",
      "description": "faster-whisper model size. Default: base.en. Options: tiny.en, base.en, small.en, medium.en, large-v3, large-v3-turbo."
    },
    {
      "name": "HF_HUB_CACHE",
      "description": "Override Hugging Face Hub cache directory where Whisper weights are stored."
    },
    {
      "name": "MCP_PRONUNCIATION_PRELOAD",
      "description": "Set to 0, false, no, or off to disable background Whisper model preload during registry inspection or Docker smoke tests."
    },
    {
      "name": "MCP_PRONUNCIATION_AUDIO_RETENTION",
      "description": "Temporary WAV retention policy. Use session to delete recordings when the server exits, or keep for manual inspection."
    },
    {
      "name": "TORCH_HOME",
      "description": "Override PyTorch cache directory for optional wav2vec2 forced-alignment weights."
    }
  ]
}

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · repository · passed · metadata changed · updated
  • · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown

Connect from your client

Each snippet configures the same source-provided package; replace placeholders before use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Cursor

Merge this local stdio configuration, replace every placeholder environment value, and restart Cursor. Koskamo has not executed this package.
Cursor configuration
{
  "mcpServers": {
    "mcp-server-pronunciation": {
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation==0.3.0"
      ],
      "env": {
        "MCP_PRONUNCIATION_MODEL": "<YOUR_MCP_PRONUNCIATION_MODEL>",
        "HF_HUB_CACHE": "<YOUR_HF_HUB_CACHE>",
        "MCP_PRONUNCIATION_PRELOAD": "<YOUR_MCP_PRONUNCIATION_PRELOAD>",
        "MCP_PRONUNCIATION_AUDIO_RETENTION": "<YOUR_MCP_PRONUNCIATION_AUDIO_RETENTION>",
        "TORCH_HOME": "<YOUR_TORCH_HOME>"
      }
    }
  }
}

Cline

Merge this local stdio configuration, replace every placeholder environment value, and restart Cline. Koskamo has not executed this package.
Cline configuration
{
  "mcpServers": {
    "mcp-server-pronunciation": {
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation==0.3.0"
      ],
      "env": {
        "MCP_PRONUNCIATION_MODEL": "<YOUR_MCP_PRONUNCIATION_MODEL>",
        "HF_HUB_CACHE": "<YOUR_HF_HUB_CACHE>",
        "MCP_PRONUNCIATION_PRELOAD": "<YOUR_MCP_PRONUNCIATION_PRELOAD>",
        "MCP_PRONUNCIATION_AUDIO_RETENTION": "<YOUR_MCP_PRONUNCIATION_AUDIO_RETENTION>",
        "TORCH_HOME": "<YOUR_TORCH_HOME>"
      }
    }
  }
}

VS Code

Merge this local stdio configuration, replace every placeholder environment value, and restart VS Code. Koskamo has not executed this package.
VS Code configuration
{
  "servers": {
    "mcp-server-pronunciation": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation==0.3.0"
      ],
      "env": {
        "MCP_PRONUNCIATION_MODEL": "<YOUR_MCP_PRONUNCIATION_MODEL>",
        "HF_HUB_CACHE": "<YOUR_HF_HUB_CACHE>",
        "MCP_PRONUNCIATION_PRELOAD": "<YOUR_MCP_PRONUNCIATION_PRELOAD>",
        "MCP_PRONUNCIATION_AUDIO_RETENTION": "<YOUR_MCP_PRONUNCIATION_AUDIO_RETENTION>",
        "TORCH_HOME": "<YOUR_TORCH_HOME>"
      }
    }
  }
}

Claude Desktop

Merge this local stdio configuration, replace every placeholder environment value, and restart Claude Desktop. Koskamo has not executed this package.
Claude Desktop configuration
{
  "mcpServers": {
    "mcp-server-pronunciation": {
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation==0.3.0"
      ],
      "env": {
        "MCP_PRONUNCIATION_MODEL": "<YOUR_MCP_PRONUNCIATION_MODEL>",
        "HF_HUB_CACHE": "<YOUR_HF_HUB_CACHE>",
        "MCP_PRONUNCIATION_PRELOAD": "<YOUR_MCP_PRONUNCIATION_PRELOAD>",
        "MCP_PRONUNCIATION_AUDIO_RETENTION": "<YOUR_MCP_PRONUNCIATION_AUDIO_RETENTION>",
        "TORCH_HOME": "<YOUR_TORCH_HOME>"
      }
    }
  }
}

Let your agent find its tools

Find servers like mcp-server-pronunciation from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.