Este es un servidor MCP que crea archivos de escenarios para el motor de juego de novela exia .
Generar un escenario en el formato "Comentario de las Hermanas Kotonoha" y mostrarlo en exia.
Generar un escenario en forma de "Comentario de las Hermanas Kotoha" para un tema determinado
Convierte el escenario generado en formato JSON para exia
Descargue exia desde GitHub y configúrelo
Visualización del escenario generado en exia
Related MCP server: VOICEPEAK MCP Server
Node.js v20.x o superior
Clave API de OpenAI
Git
Clonar o descargar el repositorio
git clone https://github.com/kokushin/exia-mcp.git
cd exia-mcpInstalar los paquetes necesarios
npm installCompilar TypeScript (ejecute esto después de realizar cualquier cambio)
npm run buildIniciar Claude Desktop
Abra la pantalla de configuración y agregue el servidor MCP
{
"mcpServers": {
"exia-scenario-generator": {
"command": "npx",
"args": [
"-y",
"/path/to/exia-mcp", //（clone した exia-mcp のパスに置き換えてください）
"--openai-api-key=YOUR_API_KEY", //（OpenAI API キーに置き換えてください）
"--stdio"
]
}
}
}※Reemplace YOUR_API_KEY con su clave API de OpenAI real.
* Si no se puede ejecutar npx , especifique la ruta absoluta.例: /path/to/.volta/bin/npx
Se utiliza en Claude Desktop de la siguiente manera:
Escribe "Explica las computadoras cuánticas en exia".
El servidor MCP se inicia, genera un escenario e inicia exia.
La aplicación exia (Electron) se inicia en una ventana separada y reproduce el escenario.
generateScenario : Generar un escenario a partir de un tema
setupExia : Descargar y configurar Exia
saveScenario : Guarda el escenario generado
exiaVoiceroidExplain : ejecuta todo, desde la generación del escenario hasta el inicio de exia (recomendado)
La primera vez que lo ejecute, tomará algún tiempo descargar y configurar exia.
Necesitarás preparar tus propias imágenes de personajes y reemplazarlas manualmente.
La documentación de exia está aquí
El uso de la API de OpenAI puede generar tarifas
Instituto Tecnológico de Massachusetts (MIT)
| Name | Required | Description | Default |
|---|---|---|---|
| topic | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| topic | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| topic | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0exiaVoiceroidExplain2 fields changedInput schema / $schemaAdded value: +"http://json-schema.org/draft-07/schema#"Input schema / additionalPropertiesAdded value: +falsegenerateScenario2 fields changedInput schema / $schemaAdded value: +"http://json-schema.org/draft-07/schema#"Input schema / additionalPropertiesAdded value: +falsesaveScenario2 fields changedInput schema / $schemaAdded value: +"http://json-schema.org/draft-07/schema#"Input schema / additionalPropertiesAdded value: +falsesetupExia1 field changedInput schema / $schemaAdded value: +"http://json-schema.org/draft-07/schema#"exiaVoiceroidExplaingenerateScenariosaveScenariosetupExiaScored across 4 tools
The tools appear to target distinct steps in a scenario generation workflow (setup, generate, save, explain), but the lack of descriptions makes it impossible to verify if there's overlap or ambiguity in their purposes. Without descriptions, an agent might guess incorrectly about boundaries, especially between generateScenario and exiaVoiceroidExplain.
Naming is inconsistent: generateScenario and saveScenario use camelCase, while exiaVoiceroidExplain and setupExia mix camelCase with unclear verb styles (e.g., 'exiaVoiceroidExplain' is a compound noun-verb hybrid). There's no predictable pattern across all tools, making them harder to parse as a set.
With 4 tools, the count is reasonable for a scenario generator server, suggesting a focused scope. It's not too thin or heavy, though the lack of descriptions makes it hard to assess if more tools might be needed for completeness.
Inferring from tool names, the domain is scenario generation with Exia/Voiceroid integration. The surface covers setup, generation, saving, and explanation, but without descriptions, it's unclear if there are gaps (e.g., listing, editing, or deleting scenarios). The absence of descriptions severely limits the ability to assess coverage, suggesting potential dead ends.
Turn a one-line story idea into a narrated anime video with BGM and subtitles, from any AI agent.
Videos, images, voices and songs from eroq's named and uncensored engines, with your characters.
Generate logos, social posts, app screenshots, comic panels & visual-novel assets from prompts.
Screenplay, film and story toolkit over MCP: PDF formatting, stats, diagnosis, video prompts.
