Add loudreader/loudkit MCP server

[tensorblock-mcp-automation]

Summary

• add loudreader/loudkit to docs/multimedia-processing.md from community issue Add MCP server: loudreader/loudkit #2310
• add structured metadata sidecar data/server-metadata/github-loudreader-loudkit-788794b9.json
• include submitted metadata below for maintainer verification

Generated entry

- [loudreader/loudkit](https://github.com/loudreader/loudkit): Lets agents speak text aloud with a local text-to-speech engine: list the 28 built-in voices (10 languages) and voice profiles cloned with the loudkit CLI, synthesize speech as base64 WAV, FLAC, MP3 or Opus with its duration and a continuation for reading long texts in pieces, and describe the loaded model. Runs on-device over stdio: no cloud, no API key.

Generated metadata sidecar

data/server-metadata/github-loudreader-loudkit-788794b9.json

{
  "$schema": "../../schemas/server-metadata.schema.json",
  "id": "github-loudreader-loudkit-788794b9",
  "source": {
    "issue": 2310,
    "projectUrl": "https://github.com/loudreader/loudkit"
  },
  "install": {
    "commands": [
      "uvx --from \"loudkit[mcp,hub]\" loudkit serve --mcp --checkpoint loudreader/loudr-1"
    ],
    "env": [],
    "confidence": "medium"
  },
  "transport": [
    "stdio"
  ],
  "auth": {
    "type": "none",
    "notes": []
  },
  "clients": [
    "Claude Code",
    "Claude Desktop",
    "Cursor",
    "Cline"
  ],
  "license": "Apache-2.0"
}

Submitted metadata

• Install: Client config command: uvx --from "loudkit[mcp,hub]" loudkit serve --mcp --checkpoint loudreader/loudr-1 Or install once with pip install "loudkit[mcp,hub]" and run loudkit serve --mcp --checkpoint loudreader/loudr-1. The first run downloads the 747 MB model and 28 voices, then it runs offline. No environment variables. Suggested category: Multimedia Processing (text-to-speech).
• Transport: stdio
• Auth: no auth
• Clients: Claude Code, Claude Desktop, Cursor, Cline
• License: Apache-2.0

Source issue

#2310

This is an automated draft PR. Maintainers should verify the project URL, category, metadata, and duplicate status before merging.