Реализация сервера Model Context Protocol (MCP) для интеграции API Smallest.ai. Этот проект предоставляет стандартизированный интерфейс для взаимодействия с системой управления базой знаний Smallest.ai.
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ │ │ │ │ │
│ Client App │◄────┤ MCP Server │◄────┤ Smallest.ai │
│ │ │ │ │ API │
└─────────────────┘ └─────────────────┘ └─────────────────┘Реализует клиентский протокол MCP
Обрабатывает форматирование запроса
Управляет анализом ответов
Обеспечивает обработку ошибок
Обработчик протоколов
Управляет коммуникацией по протоколу MCP
Обрабатывает клиентские соединения
Направляет запросы соответствующим инструментам
Реализация инструмента
Инструменты управления базой знаний
Проверка параметров
Форматирование ответа
Обработка ошибок
API-интеграция
API-коммуникация Smallest.ai
Управление аутентификацией
Обработка запросов/ответов
Управление базой знаний
Хранение и извлечение данных
Аутентификация и авторизация
1. Client Request
└─► MCP Protocol Validation
└─► Tool Parameter Validation
└─► API Request Formation
└─► Smallest.ai API Call
└─► Response Processing
└─► Client Response┌─────────────────┐
│ Client Auth │
└────────┬────────┘
│
┌────────▼────────┐
│ MCP Validation │
└────────┬────────┘
│
┌────────▼────────┐
│ API Auth │
└────────┬────────┘
│
┌────────▼────────┐
│ Smallest.ai │
└─────────────────┘Related MCP server: Rememberizer MCP Server
Этот проект реализует сервер MCP, который действует как промежуточное ПО между клиентами и API Smallest.ai. Он предоставляет стандартизированный способ взаимодействия с функциями управления базой знаний Smallest.ai через протокол контекста модели.
[Client Application] <---> [MCP Server] <---> [Smallest.ai API]MCP-сервер
Обрабатывает запросы клиентов
Управляет коммуникацией API
Предоставляет стандартизированные ответы
Реализует обработку ошибок
Инструменты базы знаний
listKnowledgeBases : список всех баз знаний
createKnowledgeBase : создает новые базы знаний
getKnowledgeBase : извлекает конкретные сведения из базы знаний
Ресурс документации
Доступно на docs://smallest.ai
Предоставляет инструкции по использованию и примеры
Node.js 18+ или среда выполнения Bun
API-ключ Smallest.ai
Знание TypeScript
Клонируйте репозиторий:
git clone https://github.com/yourusername/MCP-smallest.ai.git
cd MCP-smallest.aiУстановите зависимости:
bun installСоздайте файл .env в корневом каталоге:
SMALLEST_AI_API_KEY=your_api_key_hereСоздайте файл config.ts с конфигурацией API Smallest.ai:
export const config = {
API_KEY: process.env.SMALLEST_AI_API_KEY,
BASE_URL: 'https://atoms-api.smallest.ai/api/v1'
};bun run index.tsbun run test-client.tsСписок баз знаний
await client.callTool({
name: "listKnowledgeBases",
arguments: {}
});Создать базу знаний
await client.callTool({
name: "createKnowledgeBase",
arguments: {
name: "My Knowledge Base",
description: "Description of the knowledge base"
}
});Получить базу знаний
await client.callTool({
name: "getKnowledgeBase",
arguments: {
id: "knowledge_base_id"
}
});Все ответы имеют следующую структуру:
{
content: [{
type: "text",
text: JSON.stringify(data, null, 2)
}]
}На сервере реализована комплексная обработка ошибок:
HTTP-ошибки
Ошибки API
Ошибки проверки параметров
Типобезопасные ответы на ошибки
MCP-smallest.ai/
├── index.ts # MCP server implementation
├── test-client.ts # Test client implementation
├── config.ts # Configuration file
├── package.json # Project dependencies
├── tsconfig.json # TypeScript configuration
└── README.md # This fileОпределите инструмент в index.ts :
server.tool(
"toolName",
{
param1: z.string(),
param2: z.number()
},
async (args) => {
// Implementation
}
);Обновление документации в ресурсе:
server.resource(
"documentation",
"docs://smallest.ai",
async (uri) => ({
contents: [{
uri: uri.href,
text: `Updated documentation...`
}]
})
);Ключи API хранятся в переменных среды.
Все запросы аутентифицированы.
Реализована проверка параметров
Сообщения об ошибках очищаются
Форк репозитория
Создайте ветку функций ( git checkout -b feature/amazing-feature )
Зафиксируйте свои изменения ( git commit -m 'Add some amazing feature' )
Отправить в ветку ( git push origin feature/amazing-feature )
Открыть запрос на извлечение
Данный проект лицензирован по лицензии MIT — подробности см. в файле LICENSE .
| Name | Required | Description | Default |
|---|---|---|---|
| description | Yes | ||
| name | 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 |
|---|---|---|---|
| id | 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.
v1.0.0createKnowledgeBasegetKnowledgeBaselistKnowledgeBasesScored across 3 tools
Each tool has a clearly distinct purpose: create, get, and list operations on knowledge bases. There is no overlap in functionality, and the action verbs (create, get, list) are unambiguous and standard for CRUD operations.
All tool names follow a consistent camelCase pattern with a verb-noun structure (createKnowledgeBase, getKnowledgeBase, listKnowledgeBases). The naming is predictable and uniform across all three tools.
With only 3 tools, the set feels thin for a knowledge base management server, as it lacks update and delete operations. However, it covers basic create, retrieve, and list functions, which is minimal but functional for a small scope.
The tools provide create, get, and list operations, but there are notable gaps such as update and delete for knowledge bases. This limits full lifecycle management, though core retrieval and creation are covered.
A Model Context Protocol server for Wix AI tools
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
DocBase MCP server for AI agents
