pronounce-mcp — MCP server for the Pronounce dictionary

mcp-name: io.github.anzy-renlab-ai/pronounce

An MCP server that exposes the community pronunciation dictionary at https://pronounce.renlab.ai as tools any MCP-aware client (Claude Desktop, Continue, Zed, ...) can call.

When a user asks an LLM "how do you pronounce kubectl?", the client invokes pronounce("kubectl") and gets back the canonical reading, IPA, alternate readings (if contested), source citation, and a link to the human-readable page — without the LLM having to hallucinate.

Tools

Install (Claude Desktop)

// ~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "pronounce": {
      "command": "uvx",
      "args": ["pronounce-mcp"]
    }
  }
}

Or with pipx:

pipx install pronounce-mcp

{
  "mcpServers": {
    "pronounce": { "command": "pronounce-mcp" }
  }
}

Restart Claude Desktop. Ask any pronunciation question:

"How do you pronounce kubectl?"

Claude calls pronounce("kubectl") → gets {respelling_us: "koob control", ipa: "/ˈkuːb kənˌtroʊl/", source_label: "Kelsey Hightower (KubeCon)", url: "https://pronounce.renlab.ai/word/kubectl", ...} → answers with the canonical reading plus the citation.

Run the Node implementation from source

A zero-dependency Node (>= 18) implementation of the same server lives in npm/. It is not currently published to npm, so run it from a checkout with node mcp-server/npm/index.js. Use the PyPI package above for a registry-backed one-line install.

Why this is useful

LLMs are bad at pronunciation by default. They've seen the spelling and the IPA, but they confabulate when asked about contested words (GIF? jif or gif?) or project names with non-obvious readings (kubectl is "koob-control", not "kub-cuttle"; Pinia is "pee-nya"; Vite is "veet").

This MCP server gives the LLM a deterministic source: the dictionary is community-maintained, source-citing, and updated continuously. Every contested word has both readings with the rationale. Every "creator-clarified" reading links to where the creator settled it.

Source data

The dictionary is at https://github.com/anzy-renlab-ai/pronounce/blob/main/data/pronunciations.tsv — 1,900+ entries (and growing) across cloud / DevOps, frontend & backend frameworks, AI/ML platforms and research, databases, languages, editors, companies, programmer jargon, and acronyms.

Each entry has 10 columns: word | ipa | respelling_us | alt_ipa | alt_respelling_us | source_url | source_label | category | confidence | notes.

confidence is one of: creator-clarified (source URL documents a creator quote), community-consensus (widely used but no single citable source), or contested (multiple readings in active use).

License

MIT.