What is mocovoice-mcp-server CLAUDE.md?

Instructions for an MCP server that lets Claude Desktop use mocoVoice, a Japanese audio and video transcription service. It describes the server's Python components and its six transcription-related tools.

Use it when changing file discovery, supported formats, transcription job submission, status checks, result retrieval, or the server's API and validation code.

It gives the coding agent the project's structure, validation rules, file handling, and API responsibilities in one place. This helps changes fit the existing server design.

How mocomoco-inc/mocovoice-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mocomoco-inc/mocovoice-mcp-server. 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/mocomoco-inc/mocovoice-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mocomoco-inc/mocovoice-mcp-server

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/mocomoco-inc/mocovoice-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/mocomoco-inc/mocovoice-mcp-server/claude-md)

Your own site

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

Per session 552 This file is loaded in full into every session.

When invoked 552 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.00552	$0.00552
Opus 5.5	$0.00221	$0.00221
Sonnet 5.5	$0.00110	$0.00110
Haiku 4.5	$0.00055	$0.00055

Measured 2mo ago against content hash 88bf71c62eff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mocovoice-mcp-server CLAUDE.md 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 2mo 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.

CLAUDE.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 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.

Project Overview

This is a Model Context Protocol (MCP) server for mocoVoice, a Japanese transcription service. The server enables Claude Desktop to interact with the mocoVoice API for audio/video transcription tasks.

Architecture

The codebase follows a modular structure:

server.py: Main MCP server using FastMCP framework with 6 tools for transcription operations
api.py: HTTP client wrapper with error handling and timeout management
constant.py: Configuration constants including API endpoints, file format mappings, and error codes
utils.py: Utility functions for validation, path checking, UUID validation, and data extraction

Key Components

MCP Tools

The server exposes 6 tools:

SHOW_USAGE: Display functionality overview
SHOW_AVAILABLE_FORMATS: List supported audio/video formats
SHOW_AVAILABLE_FILES: Scan allowed directory for processable files
START_TRANSCRIPTION_JOB: Upload and start transcription job
SHOW_TRANSCRIPTION_RESULT: Retrieve completed transcription
CHECK_TRANSCRIPTION_STATUSES: List transcription history

Environment Configuration

MOCOVOICE_API_KEY: Required API key with READ/WRITE permissions
MOCOVOICE_API_URL: API endpoint (defaults to https://api.mocomoco.ai/api/v1)
ALLOWED_DIR: Directory path for accessible files (defaults to /workspace)

File Handling

Max file size: 3GB
Supported formats defined in SUPPORT_MEDIA_CONTENT_TYPES
Path validation ensures files are within allowed directory

Development Commands

Build

docker build . -t mocovoice-mcp-server

Formatting

uv run ruff format

Linting

uv run ruff check .

Testing

uv run pytest

Dependencies

httpx: Async HTTP client for API calls
mcp[cli]: Model Context Protocol framework
pytest: Testing framework
ruff: Code formatting and linting

Read the full file on GitHub · 80 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.

2mo ago First seen · 80 lines · 552 tokens per session scan A 88bf71c62eff

Subscribe to this mod's changes

mocovoice-mcp-server CLAUDE.md is an instructions file published in the GitHub repository mocomoco-inc/mocovoice-mcp-server (3 stars, last pushed 5mo ago), licensed MIT. It adds 552 tokens to every session, about $0.0022 per session on Opus 5.5. 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.

ai asr automatic-speech-recognition mcp mcp-server voice-recognition

mocovoice-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mocovoice-mcp-server CLAUDE.mdmocomoco-inc/mocovoice-mcp-server	Instructions file	3	5mo ago	MIT	A	552	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	144k	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	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	281k	today	MIT	A	4,335	Codex, OpenCode

mocovoice-mcp-server: Instructions file for Claude Code