UNO (Unified Narrative Operator) — это волшебный инструмент для улучшения текста, который превращает обычное повествование в богатые, детализированные истории. Используя передовые литературные техники и эвристический анализ, UNO может увеличить объем вашего текста вдвое, сохраняя при этом оригинальный голос и замысел автора.
Представьте UNO как своего личного помощника по повествованию, способного на следующее:
📊 Анализ текста для понимания его сильных и слабых сторон
🌱 Развитие недостаточно проработанных элементов истории
🎨 Обогащение описаний окружающей среды
⚡ Усиление динамики экшн-сцен
🌊 Улучшение плавности и ритма прозы
🔄 Устранение повторов в языке
Related MCP server: Galaxy Brain
UNO предоставляет три мощных инструмента MCP:
analyze_textВыполняет глубокий анализ страниц вашей истории и создает подробный отчет, включающий:
📝 Оценку позиции повествования (завязка, развитие, кульминация, развязка)
👤 Идентификацию фокусных персонажей
🎭 Классификацию типа сцены
🌡️ Оценку настроения и тона
📈 Рекомендации по улучшению для каждой техники
🔄 Обнаружение паттернов повторов
enhance_textПреобразует ваш текст, применяя все пять техник улучшения:
Автоматически расширяет текст до целевого объема (по умолчанию: 200%)
Интеллектуально применяет техники в зависимости от того, что больше всего нужно вашему тексту
Сбалансированно распределяет расширения по всему тексту
custom_enhance_textПредоставляет полный контроль над процессом улучшения:
Выбор техник улучшения для применения
Установка пользовательских целей расширения (100%-500%)
Фокус на конкретных аспектах вашего повествования
Выявляет недостаточно проработанные элементы в вашей истории и расширяет их:
Развивает упомянутых, но не раскрытых персонажей
Исследует подразумеваемые, но не объясненные элементы сюжета
Выявляет подтекст и скрытые смыслы
Обогащает ваши декорации иммерсивными деталями:
Добавляет яркие сенсорные ощущения (визуальные, слуховые, тактильные, обонятельные)
Создает запоминающийся фокус на незначительных объектах
Углубляет атмосферу и настроение
Превращает сцены действия в динамичные, высокоинтенсивные эпизоды:
Манипулирует восприятием времени (замедляя ключевые моменты)
Усиливает сенсорные детали во время действия
Создает ритмическое чередование между взрывным действием и мгновениями тишины
Делает окружающую среду активным участником действия
Улучшает плавность и ритм вашего письма:
Улучшает переходы между абзацами
Варьирует структуру предложений для лучшей читаемости
Создает естественный ритм, который увлекает читателей по тексту
Уменьшает непреднамеренные повторы, сохраняя стиль:
Идентифицирует и заменяет повторяющиеся слова значимыми альтернативами
Сохраняет голос и замысел автора
Различает намеренные и непреднамеренные повторы
Чтобы автоматически установить Unified Narrative Operator для Claude Desktop через Smithery:
npx -y @smithery/cli install @MushroomFleet/uno-mcp --client claudeNode.js (v14 или выше)
NPM (v6 или выше)
Клонируйте или скачайте репозиторий
git clone https://github.com/your-username/uno-mcp.git
cd uno-mcpУстановите зависимости
npm installСоберите TypeScript файлы
npm run buildСделайте сервер исполняемым (пропустите для Windows)
chmod +x dist/index.jsПротестируйте сервер
node test-run.jsЭто запустит сервер на примере истории и создаст три файла:
test-analysis.md: Пример отчета анализа
test-enhanced.txt: Пример улучшенного текста (200%)
test-custom-enhanced.txt: Пример пользовательского улучшения (150%)
Отредактируйте конфигурационный файл Claude
Windows: C:\Users\[имя_пользователя]\AppData\Roaming\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Добавьте UNO в раздел MCP-серверов
{
"mcpServers": {
"uno": {
"command": "node",
"args": ["/absolute/path/to/uno-mcp/dist/index.js"],
"disabled": false,
"autoApprove": []
}
}
}Убедитесь, что используете абсолютный путь к вашей установке UNO.
Перезапустите Claude После сохранения конфигурации перезапустите Claude, чтобы активировать MCP-сервер UNO.
Отредактируйте конфигурацию расширения Claude для VS Code
Windows: c:\Users\[имя_пользователя]\AppData\Roaming\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json
macOS: ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
Добавьте ту же конфигурацию, что показана выше для Claude Desktop.
Перезапустите VS Code или перезагрузите окно.
<use_mcp_tool>
<server_name>uno</server_name>
<tool_name>analyze_text</tool_name>
<arguments>
{
"text": "As Sarah walked into the garden, she noticed the old statue in the corner. It was covered in moss and vines, almost hidden from view. She felt drawn to it somehow."
}
</arguments>
</use_mcp_tool>Это вернет подробный отчет с анализом позиции повествования, фокуса на персонажах, возможностей для улучшения и многим другим.
<use_mcp_tool>
<server_name>uno</server_name>
<tool_name>enhance_text</tool_name>
<arguments>
{
"text": "As Sarah walked into the garden, she noticed the old statue in the corner. It was covered in moss and vines, almost hidden from view. She felt drawn to it somehow."
}
</arguments>
</use_mcp_tool>Это вернет версию вашего текста, которая примерно в два раза длиннее оригинала, с применением всех пяти техник улучшения.
<use_mcp_tool>
<server_name>uno</server_name>
<tool_name>custom_enhance_text</tool_name>
<arguments>
{
"text": "As Sarah walked into the garden, she noticed the old statue in the corner. It was covered in moss and vines, almost hidden from view. She felt drawn to it somehow.",
"expansionTarget": 150,
"enableGoldenShadow": true,
"enableEnvironmental": true,
"enableActionScene": false,
"enableProseSmoother": true,
"enableRepetitionElimination": false
}
</arguments>
</use_mcp_tool>Этот пример применяет только «Золотую тень», расширение среды и сглаживание прозы, нацеливаясь на расширение в 150%.
Can you enhance this scene with more environmental details?
<use_mcp_tool>
<server_name>uno</server_name>
<tool_name>custom_enhance_text</tool_name>
<arguments>
{
"text": "Jack entered the abandoned warehouse, searching for clues.",
"expansionTarget": 300,
"enableEnvironmental": true,
"enableGoldenShadow": false,
"enableActionScene": false,
"enableProseSmoother": false,
"enableRepetitionElimination": false
}
</arguments>
</use_mcp_tool>Let me analyze this paragraph to give you feedback:
<use_mcp_tool>
<server_name>uno</server_name>
<tool_name>analyze_text</tool_name>
<arguments>
{
"text": "[student's writing sample]"
}
</arguments>
</use_mcp_tool>
Based on the analysis, I recommend focusing on developing your character motivations more clearly.Here's a more intense version of your action scene:
<use_mcp_tool>
<server_name>uno</server_name>
<tool_name>custom_enhance_text</tool_name>
<arguments>
{
"text": "[original action scene]",
"enableActionScene": true,
"enableEnvironmental": true,
"enableGoldenShadow": false,
"enableProseSmoother": true,
"enableRepetitionElimination": true
}
</arguments>
</use_mcp_tool>Let me help you expand this chapter:
<use_mcp_tool>
<server_name>uno</server_name>
<tool_name>enhance_text</tool_name>
<arguments>
{
"text": "[chapter excerpt]",
"expansionTarget": 180
}
</arguments>
</use_mcp_tool>🔍 Всегда начинайте с analyze_text, чтобы понять, что нужно вашему тексту
🎯 Для тонких улучшений используйте custom_enhance_text с меньшей целью расширения (120-150%)
🧩 Разбивайте длинные тексты на небольшие разделы для обработки, а затем объединяйте результаты
🔄 Применяйте устранение повторов как последний шаг при улучшении крупных работ
⚡ Используйте enableActionScene: true только для сцен, содержащих элементы действия
ISC
UNO основан на передовых методах литературного улучшения и теории повествования. Особая благодарность рассказчикам, писателям и теоретикам повествования, чьи работы вдохновили этот проект.
⭐ Сделано с любовью командой UNO ⭐
TranscriptionTools-MCP — Обработка транскриптов
DeepLucid3D-MCP — Когнитивная обработка
UNO-MCP — Улучшение повествования
gitea-mcp — Интеграция с Gitea
zero-vector-MCP — Процедурная генерация
Analyzes a story page and generates a report with insights
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | The story page text to analyze or enhance |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions analysis and report generation but lacks details on what 'insights' entail, whether the operation is read-only or has side effects, performance characteristics, or error handling. This is a significant gap for a tool with no annotation coverage.
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?
The description is a single, efficient sentence that front-loads the core functionality ('Analyzes a story page') and adds the outcome ('generates a report with insights') without any wasted words. It is appropriately sized for the tool's apparent complexity.
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?
Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what the 'report' or 'insights' look like, potential limitations, or how it differs from sibling tools. For a tool with no structured behavioral or output information, more context is needed to guide effective use.
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?
The schema description coverage is 100%, with the single parameter 'text' documented as 'The story page text to analyze or enhance'. The description adds no additional parameter semantics beyond what the schema provides, so the baseline score of 3 is appropriate as the schema handles the documentation adequately.
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?
The description clearly states the tool's purpose with a specific verb ('analyzes') and resource ('a story page'), and specifies the output ('generates a report with insights'). However, it doesn't explicitly differentiate from sibling tools like 'custom_enhance_text' or 'enhance_text', which appear to have related but potentially different functions.
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?
The description provides no guidance on when to use this tool versus its siblings ('custom_enhance_text' and 'enhance_text'), nor does it mention any prerequisites, alternatives, or exclusions. It only states what the tool does without contextual usage information.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Enhances a story page using selected techniques
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | The story page text to enhance | |
| expansionTarget | No | Target expansion percentage (default: 200) | |
| enableGoldenShadow | No | Enable Golden Shadow enhancement | |
| enableEnvironmental | No | Enable Environmental expansion | |
| enableActionScene | No | Enable Action Scene enhancement | |
| enableProseSmoother | No | Enable Prose Smoothing | |
| enableRepetitionElimination | No | Enable Repetition Elimination |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'enhances' text, implying a transformation, but doesn't describe the nature of the enhancement, potential side effects, rate limits, or output format. This is a significant gap for a tool with multiple parameters and no output schema.
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?
The description is a single, efficient sentence that front-loads the core action ('enhances a story page'). It avoids unnecessary words, but could be more informative given the tool's complexity, making it slightly under-specified rather than perfectly concise.
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?
Given the tool's complexity (7 parameters, no annotations, no output schema), the description is incomplete. It doesn't explain what 'enhance' entails, how techniques interact, or what the output looks like, leaving critical gaps for an agent to understand and use the tool effectively.
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?
Schema description coverage is 100%, so the schema fully documents all 7 parameters. The description mentions 'selected techniques' but doesn't add meaning beyond the schema, which already details each enhancement technique and parameter. The baseline score of 3 reflects adequate coverage by the schema alone.
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?
The description states the tool 'enhances a story page using selected techniques,' which provides a general purpose but lacks specificity. It mentions the resource ('story page') and verb ('enhances'), but doesn't clarify what 'enhance' means or how it differs from sibling tools like 'enhance_text' and 'analyze_text', leaving the purpose somewhat vague.
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?
The description offers no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'enhance_text' or 'analyze_text', nor does it specify prerequisites, contexts, or exclusions for usage, leaving the agent without clear direction on tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Enhances a story page using all techniques to meet expansion target
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | The story page text to enhance | |
| expansionTarget | No | Target expansion percentage (default: 200) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'using all techniques' but doesn't explain what these techniques are, whether the enhancement is reversible, what permissions or rate limits apply, or what the output looks like. For a tool with no annotations and an implied mutation ('enhances'), this leaves critical behavioral traits undisclosed.
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?
The description is a single, efficient sentence that front-loads the core action. It avoids unnecessary words and gets straight to the point. However, it could be slightly more structured by explicitly separating purpose from constraints, but overall it's appropriately concise for the tool's complexity.
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?
Given the tool's implied complexity (enhancing text with multiple techniques) and lack of annotations and output schema, the description is incomplete. It doesn't explain what 'enhance' entails, what techniques are used, or what the result looks like. For a tool that likely modifies content, more context is needed to guide the agent effectively.
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?
The schema description coverage is 100%, with clear descriptions for both parameters ('text' and 'expansionTarget'). The description adds no additional meaning beyond what the schema provides, such as examples or contextual usage. However, since the schema adequately documents the parameters, a baseline score of 3 is appropriate as the description doesn't detract from the schema's clarity.
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?
The description states the tool 'enhances a story page using all techniques to meet expansion target', which provides a vague purpose. It specifies the resource ('story page') and goal ('meet expansion target'), but the verb 'enhances' is generic and doesn't clearly differentiate from sibling tools like 'analyze_text' or 'custom_enhance_text'. The description lacks specificity about what 'enhance' means operationally.
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?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'analyze_text' or 'custom_enhance_text', nor does it specify contexts, prerequisites, or exclusions for usage. The agent must infer usage based on the tool name alone, which is insufficient for informed selection.
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.
analyze_textcustom_enhance_textenhance_textScored across 3 tools
The tools 'custom_enhance_text' and 'enhance_text' have overlapping purposes, both focused on enhancing story pages, with only a vague distinction based on technique selection versus using all techniques. This creates ambiguity where an agent might struggle to choose between them for a given enhancement task. The 'analyze_text' tool is more distinct but the enhancement tools lack clear boundaries.
All tools follow a consistent snake_case naming pattern with a verb_noun structure (e.g., analyze_text, enhance_text). The naming is predictable and readable, with only minor deviation in 'custom_enhance_text' where the adjective 'custom' adds some variation but maintains the overall convention.
With only 3 tools, the server feels thin for a domain like story analysis and enhancement, potentially lacking coverage for broader operations. While it covers basic analyze and enhance functions, the low count may limit agent capabilities in handling more complex workflows or additional CRUD-like actions.
The tool set is severely incomplete for a story analysis and enhancement domain, as it only includes analysis and enhancement without any CRUD operations (e.g., create, update, delete story pages) or lifecycle management. This creates significant gaps that will likely cause agent failures when trying to perform full workflows beyond simple text processing.
Generate full stories, chapters, characters & cover art from a premise (planner-writer pipeline).
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
Fan out deep research across multiple AI providers, synthesize into one unified report.
Exactly 50 data transformation and live web verification tools for AI agents.
