Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/JuhongPark/mcp-server-pronunciationWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/juhongpark/mcp-server-pronunciation/pronunciation)<a href="https://agentmods.dev/mcp/juhongpark/mcp-server-pronunciation/pronunciation"><img src="https://agentmods.dev/badge/mcp/juhongpark/mcp-server-pronunciation/pronunciation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/juhongpark/mcp-server-pronunciation/pronunciation"><img src="https://agentmods.dev/badge/mcp/juhongpark/mcp-server-pronunciation/pronunciation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pronunciation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"pronunciation": {
"command": "uvx",
"args": [
"mcp-server-pronunciation"
],
"env": {
"MCP_PRONUNCIATION_MODEL": "",
"HF_HUB_CACHE": ""
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 12 lines scan A ac20ed940b79
pronunciation is an MCP server published in the GitHub repository JuhongPark/mcp-server-pronunciation (2 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
speech-ai
Pronunciation scoring, speech-to-text, and text-to-speech for language learning. Remote server at apim-ai-apis.azure-api.net.
vocabit-mcp
Create flashcard sets in the Vocabit app and read back how the learner actually did. Runs locally from the vocabit-mcp npm package. Needs 3 environment variables to run.
bunpro-mcp
MCP server "bunpro-mcp" as configured in PatVandyke/bunpro-mcp. Runs locally from the @patvandyke/bunpro-mcp npm package.
konid-language-coach
MCP server "konid-language-coach", hosted remotely at konid.fly.dev, as configured in robertnowell/konid-language-learning.
pronounce
MCP server for pronounce.renlab.ai — look up how engineers actually pronounce project / product / jargon names from any MCP-aware client. Runs locally from the pronounce-mcp Python package.
ielts-speaking-coach
MCP server "ielts-speaking-coach" as configured in lindsey-labs/ielts-speaking-coach. Runs ./mcp/server.mjs with node.