VOICEVOX MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VOICEVOX_URL | No | VOICEVOX APIのURL | http://localhost:50021 |
| DEFAULT_SPEED | No | デフォルトの話速 | 1.0 |
| DEFAULT_VOICE_ID | No | デフォルトの音声ID (ナースロボ_タイプT) | 47 |
| VV_MCP_STATE_DIR | No | 共有状態ファイルの保存ディレクトリ (デフォルト: システム一時ディレクトリ) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| sayA | VOICEVOXで音声合成して再生(非同期実行) |
| list_voicesB | 利用可能な音声の一覧を取得 |
| get_queue_statusB | 再生キューの状態を取得 |
| clear_queueB | 再生キューをクリア |
| get_voices_in_useA | 現在使用中の音声IDのリストを取得(全プロセス共通) |
| get_random_unused_voiceA | 使用されていない音声をランダムに1つ取得 |
| get_session_voiceA | このセッションで使用する音声を取得(セッション毎に固定) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool has a clearly distinct purpose with no ambiguity. For example, 'clear_queue' manages queue state, 'get_queue_status' retrieves status, 'get_random_unused_voice' and 'get_session_voice' handle different voice selection methods, 'get_voices_in_use' lists active voices, 'list_voices' shows all available voices, and 'say' performs synthesis and playback. The descriptions make it easy to differentiate between queue management, voice selection, and playback operations.
All tool names follow a consistent verb_noun pattern using snake_case. The verbs are clear and appropriate: 'clear', 'get', 'list', and 'say' are used consistently across tools. There are no deviations in naming conventions, making the set predictable and easy to understand at a glance.
With 7 tools, the server is well-scoped for voice synthesis and playback management. Each tool serves a specific function in the workflow, from listing voices and managing queues to synthesizing speech. The count is neither too sparse nor bloated, fitting the domain of a VOICEVOX interface effectively.
The tool set covers core operations for voice synthesis, including voice listing, selection, queue management, and playback. Minor gaps exist, such as the lack of tools for modifying queue order or stopping playback, but agents can work around these using the provided tools (e.g., clearing the queue). Overall, it supports essential workflows without dead ends.