How do I use max-docs?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@max-docs find docs for the sendMessage endpoint" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

max-docs

by Launchery

Overview Schema Related Servers Score Discussions

TypeScript

Local

MAX Platform Docs MCP Server

MCP-сервер с локальной документацией по MAX Platform для AI-кодинг-агентов. После сборки сервер отдаёт документацию через stdio и покрывает не только MAX Bot API, но и руководства, mini apps / MAX Bridge API и библиотеку UI-компонентов.

Что покрывает проект

29 эндпоинтов MAX Bot API
26 моделей данных
20 руководств в 8 категориях
MAX Bridge API для мини-приложений: 6 объектов и 17 событий
35 UI-компонентов MAX UI
8 MCP tools (поиск с фильтрами, примеры кода, endpoint lookup)
4 MCP prompts (создание бота, паттерны сообщений, мини-приложения, диагностика)
Расширенный набор resources с автодополнением

Related MCP server: MCP Framework Documentation Server

Требования

Node.js >= 18
npm >= 8

Проверка:

node --version
npm --version

Установка и сборка

git clone https://github.com/Launchery/max_docs_mcp.git
cd max_docs_mcp
npm install
npm run build

Точка входа после сборки: dist/index.js.

Для локального запуска из корня репозитория уже есть пример в ./.mcp.json.

Быстрый старт

git clone https://github.com/Launchery/max_docs_mcp.git
cd max_docs_mcp
npm install
npm run build
echo "$(pwd)/dist/index.js"

Дальше подключите этот путь к вашему MCP-клиенту как stdio-сервер:

{
  "mcpServers": {
    "max-docs": {
      "command": "node",
      "args": ["/absolute/path/to/max_docs_mcp/dist/index.js"]
    }
  }
}

Подключение к клиентам

Сервер использует stdio, поэтому схема везде одна и та же: клиент запускает node <path>/dist/index.js как дочерний процесс.

Claude Code

claude mcp add --scope user max-docs -- node "/absolute/path/to/max_docs_mcp/dist/index.js"

Проверка в сессии:

/mcp

Claude Desktop

Добавьте блок mcpServers.max-docs в claude_desktop_config.json:

{
  "mcpServers": {
    "max-docs": {
      "command": "node",
      "args": ["/absolute/path/to/max_docs_mcp/dist/index.js"]
    }
  }
}

Cursor

Создайте .cursor/mcp.json в рабочем проекте:

{
  "mcpServers": {
    "max-docs": {
      "command": "node",
      "args": ["/absolute/path/to/max_docs_mcp/dist/index.js"]
    }
  }
}

Windsurf

Добавьте тот же stdio-сервер в mcp_config.json:

{
  "mcpServers": {
    "max-docs": {
      "command": "node",
      "args": ["/absolute/path/to/max_docs_mcp/dist/index.js"]
    }
  }
}

VS Code + Continue

mcpServers:
  - name: max-docs
    command: node
    args:
      - /absolute/path/to/max_docs_mcp/dist/index.js

OpenAI Codex CLI

{
  "mcpServers": {
    "max-docs": {
      "command": "node",
      "args": ["/absolute/path/to/max_docs_mcp/dist/index.js"]
    }
  }
}

Или через флаг:

codex --mcp-config '{"max-docs":{"command":"node","args":["/absolute/path/to/max_docs_mcp/dist/index.js"]}}'

OpenCode CLI

[mcp.max-docs]
type = "stdio"
command = "node"
args = ["/absolute/path/to/max_docs_mcp/dist/index.js"]

Demo

Для быстрой записи GIF / скринкаста / терминального демо см. DEMO-SCRIPT.md.

Короткая версия demo path:

npm install && npm run build
показать MCP config с max-docs
показать успешный initialize
показать tools/call для list_guides или search_docs

Проверка работоспособности

Сборка:

npm run build

Прямой запуск:

npm start

Сервер должен запуститься и ждать JSON-RPC сообщения по stdin.

Проверка initialize вручную:

echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0.0"}}}' | node dist/index.js

В ответе должны быть:

"name": "max-docs"
"version": "2.0.0"

Проверка tool-вызова вручную:

printf '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0.0"}}}\n{"jsonrpc":"2.0","method":"notifications/initialized"}\n{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"list_guides","arguments":{}}}\n' | node dist/index.js 2>/dev/null

Доступные tools

Сервер регистрирует 7 инструментов.

Tool	Аргументы	Что возвращает
`list_endpoints`	нет	Таблицу всех 29 эндпоинтов MAX Bot API
`get_endpoint`	`method`, `path`	Полную документацию конкретного эндпоинта
`search_docs`	`query`	Поиск по endpoint-ам, моделям, guide-ам, Bridge API и UI-компонентам
`list_guides`	`category?`	Список всех guide-ов или guide-ов выбранной категории
`get_guide`	`id`	Полный текст guide-а по ID
`get_bridge_api`	`object?`	Обзор MAX Bridge API, объект Bridge API или список событий
`get_component`	`name?`	Обзор MAX UI или описание конкретного компонента

Категории для `list_guides`

platform
chatbot
tutorials
sdk
mini-apps
channels
partners
legal

Доступные guide ID

connection-guide
service-selection
bot-creation
nocode-bot-creation
bot-management
bot-coding-preparation
hello-bot-javascript
hello-bot-go
sdk-javascript
sdk-go
channel-creation
channel-management
partner-integration
legal-rules
legal-requirements
legal-agreement
legal-privacy
bridge-api
mini-apps-introduction
data-validation

Доступные Bridge API объекты

BackButton
ScreenCapture
HapticFeedback
BiometricManager
DeviceStorage
SecureStorage
events

Примеры компонентов для `get_component`

Button
Input
Avatar.Container
Flex
Typography.Title
Profile

Доступные resources

API и модели

max-docs://overview
max-docs://api/bot
max-docs://api/chats
max-docs://api/pinned-messages
max-docs://api/members
max-docs://api/messages
max-docs://api/subscriptions
max-docs://api/uploads
max-docs://api/callbacks
max-docs://models
max-docs://models/{name}

Руководства

max-docs://guides
max-docs://guides/platform
max-docs://guides/chatbot
max-docs://guides/tutorials
max-docs://guides/sdk
max-docs://guides/mini-apps
max-docs://guides/channels
max-docs://guides/partners
max-docs://guides/legal
max-docs://guides/{id}

Mini apps / Bridge API

max-docs://mini-apps
max-docs://mini-apps/bridge-api
max-docs://mini-apps/bridge-api/events
max-docs://mini-apps/bridge-api/{name}

UI components

max-docs://ui-components
max-docs://ui-components/{name}

Примеры запросов к агенту

Покажи все эндпоинты MAX Bot API и объясни, какой использовать для отправки сообщения.

Используй документацию MAX и покажи guide по созданию чат-бота.

Какие события есть у MAX Bridge API и как слушать кнопку "назад"?

Найди в MAX UI компонент Button и покажи его параметры.

Подскажи, как валидировать данные мини-приложения в MAX.

Структура проекта

max_docs_mcp/
├── .mcp.json
├── README.md
├── package.json
├── tsconfig.json
├── src/
│   ├── index.ts
│   ├── server.ts
│   ├── data/
│   │   ├── overview.ts
│   │   ├── types.ts
│   │   ├── endpoints/
│   │   ├── models/
│   │   ├── guides/
│   │   ├── mini-apps/
│   │   └── ui-components/
│   ├── resources/
│   │   └── registry.ts
│   ├── tools/
│   │   ├── list-endpoints.ts
│   │   ├── get-endpoint.ts
│   │   ├── search-docs.ts
│   │   ├── list-guides.ts
│   │   ├── get-guide.ts
│   │   ├── get-bridge-api.ts
│   │   └── get-component.ts
│   └── utils/
│       ├── formatter.ts
│       └── search.ts
└── dist/

Разработка

Режимы работы:

npm run build
npm run dev
npm start

Если вы добавляете новую документацию:

Обновите соответствующий файл в src/data/...
Добавьте экспорт в нужный index.ts
Если появляется новый MCP tool или resource, зарегистрируйте его в src/server.ts или src/resources/registry.ts
Пересоберите проект через npm run build

Устранение неполадок

Сервер не запускается

npm run build
node dist/index.js

Если процесс не падает сразу, сервер стартует корректно и ждёт stdin.

Клиент не видит MCP-сервер

Проверьте, что указан абсолютный путь к dist/index.js
Пересоберите проект: npm run build
Перезапустите MCP-клиент после изменения конфигурации
Для Claude Code проверьте /mcp

Документация выглядит старой

git pull
npm install
npm run build

Ошибка `Cannot find module`

Переустановите зависимости и пересоберите проект:

rm -rf node_modules dist
npm install
npm run build

MCP Registry

Сервер подготовлен для submission в MCP Registry. Файл server.json содержит метаданные для публикации.

# После npm publish
# Submit to MCP Registry (requires GitHub auth)
curl -X POST https://registry.modelcontextprotocol.io/v0/publish \
  -H "Authorization: Bearer $MCP_REGISTRY_TOKEN" \
  -H "Content-Type: application/json" \
  --data @server.json

Available Tools

8 tools

get_bridge_apiA

Документация MAX Bridge API (window.WebApp) для мини-приложений. Без параметров — обзор. С параметром — конкретный объект (BackButton, HapticFeedback и др.) или "events" для списка событий.

ParametersJSON Schema

Name	Required	Description	Default
`object`	No	Имя объекта Bridge API (BackButton, HapticFeedback, BiometricManager, ScreenCapture, DeviceStorage, SecureStorage) или "events"

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since no annotations are provided, the description must reveal behavioral traits. It discloses the conditional output based on parameter presence, names example objects, and mentions the 'events' option. It does not describe response structure or permissions, but for a read-only documentation tool this is sufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that conveys all essential information without redundancy. It states the subject, explains the two modes, and gives examples, earning its place with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one optional parameter and no output schema, the description covers the two invocation modes and hints at return values (overview, object, events). It is nearly complete; slightly more detail about the structure of the returned documentation could make it perfect.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already lists valid values with 100% coverage. The description adds the critical semantic that omitting the parameter yields an overview, which is not encoded in the schema (since the parameter is optional). This extra context clarifies the parameter's behavioral effect beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states that the tool provides documentation for the MAX Bridge API (window.WebApp) and clearly distinguishes its behavior based on the optional parameter: an overview without parameters, or a specific object/events with a parameter. This is specific and differentiates it from sibling documentation tools like list_endpoints or get_endpoint.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear usage context: use without parameters for an overview, with a parameter for a specific object (e.g., BackButton, HapticFeedback) or 'events' for event listings. It does not explicitly mention alternatives or exclusions, but the parameter-dependent guidance is practical and unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_code_exampleB

Получить пример кода для типичной задачи MAX Bot API. Доступно: send-message, send-buttons, handle-callback, webhook-setup, mini-app-init, upload-file, bridge-storage, error-handling.

ParametersJSON Schema

Name	Required	Description	Default
`task`	Yes	Задача или ключевой слово (например: "send message", "buttons", "webhook", "mini-app", "upload", "error")

TDQS

B3.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It explains the tool's action and available task values, but does not mention response format, error handling for unsupported tasks, or any limitations. For a read-only retrieval tool, this is minimal disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: one sentence plus a list. It front-loads the core action and immediately follows with the list of supported tasks. There is no redundant or filler content, and every part adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a single parameter and no output schema, the description covers the tool's core purpose and supported tasks adequately. However, it omits details about the return type or structure of the code example, and does not discuss behavior when an invalid task is provided. This leaves some gaps for a tool operating without annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema describes the 'task' parameter generically with examples, but the tool description adds a comprehensive enumeration of valid task keywords (send-message, webhook-setup, etc.). This supplements the schema's coverage and helps the agent select a valid value, exceeding the baseline for 100% schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: getting a code example (Получить пример кода) for a typical MAX Bot API task. It enumerates eight supported tasks, which distinguishes it from sibling tools like get_endpoint or get_guide. However, it does not explicitly reference alternatives, so it falls slightly short of a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage: if one of the listed tasks matches your need, use this tool. It lists valid task keywords but does not explicitly state when to use this instead of other documentation tools, nor does it mention exclusions or prerequisites. The usage guidance is present but implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_componentA

Документация MAX UI компонентов. Без параметров — обзор библиотеки. С параметром — конкретный компонент (Button, Input, Avatar.Container и др.).

ParametersJSON Schema

Name	Required	Description	Default
`name`	No	Имя компонента (например: Button, Input, Avatar.Container, Flex)

TDQS

A4.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses the dual behavior (overview vs specific component) which is useful. However, it does not mention what the output format is, whether authentication is required, or how invalid names are handled. For a documentation lookup tool, this is acceptable but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise, with two short sentences that convey the purpose, usage, and examples. Every word earns its place, and it is well-structured with a clear distinction between the two parameter states.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the tool (one optional parameter, no output schema), the description covers the essential behavior and usage. It lacks explicit information about the return format or error behavior, but for a documentation tool this is unlikely to confuse an agent. The description is sufficiently complete for most invocations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema's 'name' parameter already has a clear description with examples. The tool description adds meaningful context by explaining that omitting the parameter yields an overview and including it yields a specific component. This goes beyond the schema's basic description, so the baseline of 3 is raised to 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: it provides documentation for MAX UI components. It specifies two modes: without parameters it returns a library overview, and with a parameter it returns a specific component (Button, Input, Avatar.Container, etc.). This distinguishes it from sibling tools like get_endpoint and get_guide.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear usage instructions: call without parameters for an overview, or pass a component name to get details. It does not explicitly name alternative tools or list exclusions, but the context makes the intended use evident.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_endpointA

Возвращает полную документацию конкретного эндпоинта MAX Bot API по методу и пути

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	Путь эндпоинта, например /messages или /chats/{chatId}
`method`	Yes	HTTP метод

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full burden. It discloses that the tool returns complete documentation for an endpoint, which implicitly indicates a read-only operation. However, it does not mention error handling, required permissions, or any edge cases, leaving some behavioral aspects undisclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the action and resource. Every word contributes to the meaning, with no filler or repetition. It is appropriately concise for the tool's simple purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 fully described parameters, no output schema), the description is largely complete. It states what is returned (full documentation) and the required inputs. It could be more explicit about the output format, but for a straightforward documentation lookup, this is sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and both parameters ('method' and 'path') have descriptions. The description's phrase 'по методу и пути' (by method and path) adds little beyond the schema. Since the schema already fully documents parameters, a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Возвращает' (returns) and the specific resource 'полную документацию конкретного эндпоинта' (full documentation of a specific endpoint). It is differentiated from sibling tools like list_endpoints and search_docs by focusing on a single endpoint by method and path.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context on when to use the tool: when you need full documentation for a specific endpoint, identified by method and path. It does not explicitly mention alternatives or exclusions, but the purpose itself implies the appropriate usage scenario.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_guideA

Возвращает полное руководство по ID. Используйте list_guides для просмотра доступных ID.

ParametersJSON Schema

Name	Required	Description	Default
`id`	Yes	ID руководства, например: bot-creation, sdk-javascript, hello-bot-go

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description must bear the burden of disclosure. It states that the tool returns a complete guide, but does not detail return format, error handling, or any potential side effects. However, as a read-only get operation, the behavior is largely predictable; a 3 is appropriate for a simple, honest description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is highly concise: two short sentences, with the primary function front-loaded and a useful cross-reference to list_guides. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple single-parameter retrieval tool, the description provides sufficient context: it explains what is returned (full guide) and how to obtain valid IDs (list_guides). The lack of an output schema is not a critical gap given the tool's straightforward nature.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already has a rich description for the 'id' parameter with concrete examples, covering 100% of parameter documentation. The description adds no additional parameter semantics, so the baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states that the tool returns a full guide by ID, using a clear verb ('returns') and a specific resource ('guide'). It also distinguishes itself from sibling tools by mentioning list_guides for discovering available IDs, clarifying its role as a direct lookup.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides a clear usage hint: use list_guides to find IDs before calling get_guide. While it doesn't mention other alternatives like search_docs, it gives sufficient context for when this tool is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_endpointsA

Возвращает таблицу всех эндпоинтов MAX Bot API с методом, путём и описанием

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses that the tool returns a table and lists the contents (method, path, description), which is the primary behavior. For a simple read-only listing tool, this is sufficient, though it does not mention potential limitations or error conditions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence containing exactly the necessary information: what is returned and what it includes. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter listing tool with no output schema and no annotations, the description is complete: it states the return type and the exact columns provided. No additional context is needed for the tool's intended use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has no properties, so there are zero parameters. Baseline for 0 params is 4, and the description correctly does not attempt to explain non-existent parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: returning a table of all MAX Bot API endpoints with method, path, and description. The verb 'Возвращает' (returns) and resource 'таблицу всех эндпоинтов' are specific, and the scope ('всех') distinguishes it from sibling tools like get_endpoint.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

While the description implies when to use this tool (when needing an overview of all endpoints), it does not explicitly state exclusions or alternatives. No mention of using get_endpoint for specific endpoints. The guidance is implicit only.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_guidesA

Список всех руководств документации MAX: платформа, создание ботов, SDK, мини-приложения, каналы, партнёры, юридические документы

ParametersJSON Schema

Name	Required	Description	Default
`category`	No	Фильтр по категории (опционально)

TDQS

A3.6/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description must fully disclose behavior. It states the scope ('all guides') but does not mention the return format, pagination, ordering, or filtering behavior beyond the schema's optional category field. This is minimal transparency for a listing operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that directly states the tool's purpose and enumerates the covered topics. Every word earns its place; there is no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a low-complexity list tool with one optional enum parameter, the description adequately conveys scope and category coverage. However, since there is no output schema, a brief note about the return structure or how this relates to get_guide for detailed viewing would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage for the single optional 'category' parameter is 100%, including an enum and a description. The tool description lists categories in prose, but this largely duplicates the schema and adds no meaningful semantic detail beyond what is already structured.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('list') and resource ('all MAX documentation guides'), and enumerates specific categories (platform, bot creation, SDK, mini-apps, channels, partners, legal). This distinguishes it from sibling tools like get_guide (retrieving a single guide) and list_endpoints.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies a generic listing use case but does not explicitly state when to use this tool versus get_guide, search_docs, or list_endpoints. No exclusions or alternative recommendations are provided; the category filter is only present in the schema, not described in the tool description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_docsA

Поиск по всей документации MAX: эндпоинты, модели, руководства, Bridge API, UI-компоненты. Поддерживает фильтрацию по типу и категории.

ParametersJSON Schema

Name	Required	Description
`type`	No	Фильтр по типу: endpoint, model, guide, bridge, component (по умолчанию: all)
`query`	Yes	Поисковый запрос (ключевые слова)
`category`	No	Фильтр по категории: messages, chats, members, bot, subscriptions, uploads, callbacks, mini-apps, ui (опционально)

TDQS

A3.5/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. It discloses the search scope and filtering capability, but does not specify return format, result limits, authorization requirements, or other behavioral details. This is a significant gap given the absence of annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences, front-loaded with the core purpose and content scope. The second sentence adds filtering capabilities without redundancy. It achieves clarity in minimal words, earning a perfect score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is a search across all docs, with schema covering the parameters adequately. However, the description does not explain return values, which is important since no output schema exists. The absence of authorization or result format details leaves the agent somewhat uncertain about the tool's behavior, but the core purpose is clear enough for basic invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema covers all parameters with descriptions, so baseline is 3. The description adds context that type and category serve as filters, aligning with schema, but does not add meaningful detail beyond what the schema provides. The query parameter is adequately described in the schema, maintaining the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool performs a search across all MAX documentation, listing specific content types (endpoints, models, guides, Bridge API, UI components). It distinguishes itself from sibling tools by covering all documentation types and offering filtering. The verb 'search' and resource 'docs' are specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this is the broad search tool, while sibling tools are direct accessors, but it does not explicitly state when to use search_docs instead of specific getters. No explicit alternatives or exclusions are mentioned. This leaves the agent to infer usage context, which is clear but not explicitly guided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

8 tool updatesv2.0.0Aug 10, 2026
- First observedget_bridge_api
- First observedget_code_example
- First observedget_component
- First observedget_endpoint
- First observedget_guide
- First observedlist_endpoints
- First observedlist_guides
- First observedsearch_docs

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.1/5.0

Disambiguation5/5

Each tool targets a distinct documentation aspect: endpoints, guides, bridge API, components, code examples, and general search. No two tools overlap in purpose; even get_bridge_api and get_component use parameters to switch between overview and detail, avoiding duplicate tools.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern: list_endpoints, get_endpoint, search_docs, list_guides, get_guide, get_bridge_api, get_component, get_code_example. The verbs 'list', 'get', and 'search' are used predictably according to the action.

Tool Count5/5

8 tools is well-scoped for a documentation server. Each tool covers a necessary function without redundancy, providing a comprehensive but manageable set for users to explore MAX documentation.

Completeness5/5

The server covers the full lifecycle of documentation access: listing endpoints, retrieving endpoint details, searching across all docs, listing guides, retrieving guides, accessing Bridge API docs, component docs, and code examples. No obvious gaps exist for the stated purpose.

Maintenance

ActivityInactive

ResponsivenessUnresponsive

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Airbyte AgentsOAuth
io.github.airbytehq
Let AI agents query data and act across all your business apps via MCP.
Data Platforms AI & Machine Learning RAG Systems
2
mcp
dev.augments
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
Developer Tools Documentation Access
2128
PropelAgent StudioOAuth
io.github.contacto291
AI agent platform: manage leads, conversations, bots, calendar and CRM via MCP.
CRM Communication Agent Orchestration
2
IFTTT MCP serverOAuth
com.ifttt
Automate 1,000+ services from any MCP-compatible AI agent: build Applets, run actions and queries.
App Automation
1

Related MCP Servers

Knowledge Server
Documentation Access API Testing Search
atnguyen143
F
license
Not graded
quality
Not graded
maintenance
Provides LLM-agnostic access to API documentation through MCP and REST endpoints, enabling AI assistants to retrieve, search, and proxy requests to whitelisted APIs across multiple platforms.
Updated 8 months ago (2025-12-27 16:06 UTC)
-
MCP Framework Documentation
Documentation Access Developer Tools Search
QuantGeekDev
A
license
A
quality
D
maintenance
Provides tools for AI agents to search, browse, and retrieve the full documentation for the mcp-framework. It enables agents to access documentation sections and page content directly within MCP-compatible environments like Claude Code and Cursor.
Updated 5 months ago (2026-04-01 17:57 UTC)
3
19
MIT
@prosodyai/mcp-docsofficial
Documentation Access Developer Tools
ProsodyAI
A
license
A
quality
B
maintenance
Exposes ProsodyAI documentation, SDK references, REST API reference (OpenAPI), and curated implementation recipes to AI coding agents via MCP tools and resources.
Updated a month ago (2026-07-23 06:49 UTC)
8
MIT
Keboola API Documentation MCPofficial
Documentation Access Developer Tools
keboola
F
license
Not graded
quality
D
maintenance
Give your AI agents instant access to Keboola API documentation. Search endpoints, get parameter details, and generate curl examples—all through MCP tools.
Updated a month ago (2026-08-05 00:02 UTC)
-

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Launchery/max_docs_mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

MAX Platform Docs MCP Server

Что покрывает проект

Требования

Установка и сборка

Быстрый старт

Подключение к клиентам

Claude Code

Claude Desktop

Cursor

Windsurf

VS Code + Continue

OpenAI Codex CLI

OpenCode CLI

Demo

Проверка работоспособности

Доступные tools

Категории для list_guides

Доступные guide ID

Доступные Bridge API объекты

Примеры компонентов для get_component

Доступные resources

API и модели

Руководства

Mini apps / Bridge API

UI components

Примеры запросов к агенту

Структура проекта

Разработка

Устранение неполадок

Сервер не запускается

Клиент не видит MCP-сервер

Документация выглядит старой

Ошибка Cannot find module

MCP Registry

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

@prosodyai/mcp-docsofficial

Keboola API Documentation MCPofficial

Latest Blog Posts

MCP directory API

Категории для `list_guides`

Примеры компонентов для `get_component`

Ошибка `Cannot find module`