What is mcp-tts-voicevox CLAUDE.md?

Repository instructions for mcp-tts-voicevox, a workspace of TypeScript packages that provides text-to-speech through Voicevox.

Use them when developing or validating this project, especially when selecting the correct pnpm package and script.

They define the required package manager and the commands for building, checking, testing, and running the whole workspace or one package.

How kajidog/mcp-tts-voicevox configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kajidog/mcp-tts-voicevox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/kajidog/mcp-tts-voicevox/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kajidog/mcp-tts-voicevox

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kajidog/mcp-tts-voicevox/claude-md/github.svg)](https://agentmods.dev/instructions/kajidog/mcp-tts-voicevox/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kajidog/mcp-tts-voicevox/claude-md"><img src="https://agentmods.dev/badge/instructions/kajidog/mcp-tts-voicevox/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/kajidog/mcp-tts-voicevox/claude-md"><img src="https://agentmods.dev/badge/instructions/kajidog/mcp-tts-voicevox/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,803 This file is loaded in full into every session.

When invoked 2,803 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.02803	$0.02803
Opus 5.5	$0.01121	$0.01121
Sonnet 5.5	$0.00561	$0.00561
Haiku 4.5	$0.00280	$0.00280

Measured 18d ago against content hash 5807d9f5ccac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-tts-voicevox CLAUDE.md scanned grade A with 1 finding 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 18d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

`packages/voicevox-client/vitest.config.ts` aliases `node-playback-strategy` to `src/__mocks__/node-playback-strategy.ts` to avoid loading `child_process.spawn` in tests. When adding new playback strategies, update this

CLAUDE.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

Package manager is pnpm. Do not use npm or yarn.

The root package.json is private and holds no source — it exists only to pin packageManager (pnpm 10), host the shared devDependencies (Biome, Changesets), and expose workspace-wide scripts. Run scripts from the root, or scope them with pnpm --filter <package> <script>.

Build & Validate (whole workspace)

pnpm build - Build every package (tsgo / tsup / vite depending on the package)
pnpm lint - Biome check across all packages in one pass
pnpm typecheck - tsc --noEmit in each package
pnpm test - Run Vitest across packages

Lint is deliberately a single root invocation: biome.json's includes already covers every package, so pnpm -r lint would re-check the same files. Type checking stays per-package because each has its own tsconfig.

Per-package

pnpm --filter @kajidog/mcp-tts-voicevox dev - Start MCP server in stdio mode via tsx
pnpm --filter @kajidog/mcp-tts-voicevox dev:http - Start MCP server in HTTP mode via tsx
pnpm --filter @kajidog/mcp-tts-voicevox dev:bun - Start MCP server via Bun (TypeScript direct execution)
cd apps/mcp-tts && pnpm test / pnpm build / pnpm typecheck
cd packages/voicevox-client && pnpm test / pnpm build / pnpm typecheck

Run a Single Test

cd apps/mcp-tts && pnpm vitest run src/__tests__/config.test.ts
cd packages/voicevox-client && pnpm vitest run src/__tests__/prefetch.test.ts

Architecture

VOICEVOX MCP server for text-to-speech. Four workspace packages with strict separation:

Packages

Package	Path	Purpose	Build	Runtime Dependencies
`@kajidog/mcp-tts-voicevox`	`apps/mcp-tts/`	MCP server (stdio + HTTP modes), npm bin	tsup	MCP SDK, ext-apps, Zod, voicevox-client (+ mcp-core bundled)
`@kajidog/voicevox-client`	`packages/voicevox-client/`	Standalone TTS library (npm-publishable)	tsgo	Zero (native fetch, crypto.randomUUID)
`@kajidog/mcp-core`	`packages/mcp-core/`	Shared MCP server infrastructure (config, HTTP, launcher, stdio)	tsgo	MCP SDK, Hono, @hono/node-server, Zod
`@kajidog/player-ui`	`packages/player-ui/`	MCP Apps audio player UI (React, bundled to a single HTML)	vite	React, ext-apps

Read the full file on GitHub · 145 lines

Changes

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.

18d ago Changed · -2 tokens per session 5807d9f5ccac
2mo ago First seen · 145 lines · 2,805 tokens per session scan A 7c3a2a5598b4

Subscribe to this mod's changes

mcp-tts-voicevox CLAUDE.md is an instructions file published in the GitHub repository kajidog/mcp-tts-voicevox (16 stars, last pushed 2d ago), licensed ISC. It adds 2,803 tokens to every session, about $0.0112 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

mcp mcp-apps mcp-server

mcp-tts-voicevox CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-tts-voicevox CLAUDE.mdkajidog/mcp-tts-voicevox	Instructions file	16	2d ago	ISC	A	2,803	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

mcp-tts-voicevox: Instructions file for Claude Code