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/GoRakuDo/yomitan-mcpWrote 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/gorakudo/yomitan-mcp/yomitan-mcp-server)<a href="https://agentmods.dev/mcp/gorakudo/yomitan-mcp/yomitan-mcp-server"><img src="https://agentmods.dev/badge/mcp/gorakudo/yomitan-mcp/yomitan-mcp-server/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/gorakudo/yomitan-mcp/yomitan-mcp-server"><img src="https://agentmods.dev/badge/mcp/gorakudo/yomitan-mcp/yomitan-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
yomitan-mcp-server 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 11d 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
{ "yomitan-mcp-server": { "command": "npx", "args": [ "-y", "yomitan-mcp-server" ] } }
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.
- 11d ago First seen · 9 lines scan A 87b1e97c211b
yomitan-mcp-server is an MCP server published in the GitHub repository GoRakuDo/yomitan-mcp (6 stars, last pushed 6mo ago), licensed MPL-2.0. 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
anki-mcp-stdio
MCP server "anki-mcp-stdio" as configured in ankimcp/anki-mcp-server. Launched with ankimcp --stdio.
anki-mcp-server
MCP server for Anki flashcards: adaptive review, notes, media, and deck management via AnkiConnect. Runs locally from the @ankimcp/anki-mcp-server npm package.
anki-mcp-http
MCP server "anki-mcp-http", hosted remotely at localhost, as configured in ankimcp/anki-mcp-server.
lingochunk
Model Context Protocol server for the LingoChunk public API: your FSRS-graded vocabulary, native-audio transcripts and clips, and library, as tools for a coding agent. Runs locally from the @lingochunk/mcp npm package. Needs 1 environment variable to run.
yanki-mcp-server
A Model Context Protocol server for interacting with Anki flashcards. Runs locally from the yanki-mcp-server npm package.
anki-mcp-server
MCP server for Anki. Runs locally from the @loonskai/anki-mcp-server npm package.