Skip to content
MCP server

Pronounce

Look up how developers say kubectl, nginx, YAML and nearly 2,000 other terms

Runs locallyStatus and history
Pricing
Free
Platforms
CLI, Web, vscode
Runs
Locally
Version
0.2.0
Listing updated
3 days ago

About Pronounce

Pronounce is a free MCP server for developer tools. It runs locally on your machine and is started by your AI client.

Settled arguments and open ones sit side by side. The dictionary tags each entry as creator-clarified, community-consensus or contested, and attaches a citable source where one exists, such as a creator's talk or an RFC; it leaves the source blank rather than invent one. Examples from the README include GIF as "jif" per its creator, nginx as "engine X" and JWT as "jot" per RFC 7519.

Entries include IPA and audio. The registry entry cites 1,927 entries, while the README and website quote slightly different totals, with roughly two thirds carrying a citable source.

The MCP server runs over stdio (PyPI or an OCI image) so an agent can check how to say a term. The same dictionary is available as a say-it command-line tool, a VS Code extension, a Claude Code skill, a quiz and a browser site, and corrections arrive by pull request.

Install

Run in a terminal

claude mcp add pronounce -- uvx pronounce-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "pronounce": {
      "command": "uvx",
      "args": [
        "pronounce-mcp"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "pronounce": {
      "command": "uvx",
      "args": [
        "pronounce-mcp"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "pronounce": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "pronounce-mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "pronounce": {
      "command": "uvx",
      "args": [
        "pronounce-mcp"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "pronounce": {
      "command": "uvx",
      "args": [
        "pronounce-mcp"
      ]
    }
  }
}

What it does

Confidence tags
Entries are marked creator-clarified, community-consensus or contested.
Cited sources
Each entry links a source where one exists.
IPA and audio
Every entry includes IPA and a spoken version.
Command-line lookup
say-it kubectl pronounces a term from the shell.
Several front ends
Browser site, VS Code extension, Claude Code skill and MCP server.
Community corrections
Disputed readings are settled through pull requests with sources.

Good for

  • Check how to say a tool name before a talk
  • Settle a team argument about SQL or JSON with a citation
  • Have an agent add pronunciations to docs or scripts
  • Practise jargon with the built-in quiz

Pricing

Free

Prices change. Check pronounce.renlab.ai before you buy.

Pronounce FAQ

How many entries are there?

Close to 2,000; the registry cites 1,927 and the README cites 1,973, most with a source.

How are disputed words handled?

They are tagged contested and both readings are listed.

How do I install the MCP server?

From PyPI as pronounce-mcp, or as an OCI image.

Can I fix a pronunciation?

Yes, open a pull request with your reading and a source.

Is Pronounce free?

Yes. Pronounce is free to use.

How do I add Pronounce to Claude Code?

Run this command in your terminal: claude mcp add pronounce -- uvx pronounce-mcp

What are the best alternatives to Pronounce?

The closest alternatives to Pronounce are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Pronounce

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools