Skip to main content
Glama
deenesjakoruzh
jimbul

You.com MCP Server

by jimbul
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

MCP-сервер You.com

Этот сервер MCP (Model Context Protocol) предоставляет помощникам ИИ возможность поиска в Интернете, получения новостей и проведения исследований с использованием API You.com. Обратная связь приветствуется.

Функции

  • Веб-поиск : доступ к функциям веб-поиска You.com

  • Умный поиск : ответы на основе искусственного интеллекта с поддержкой цитирования

  • Исследования : всесторонние, подкрепленные цитатами ответы на академические вопросы

  • Поиск новостей : Последние новостные статьи на любую тему

Related MCP server: Kagi MCP Server

Предпосылки

  • Node.js (v16 или выше)

  • npm или пряжа

  • Ключ API You.com (получите его на api.you.com )

Установка

  1. Клонируйте этот репозиторий:

    git clone https://github.com/jimbul/youcom-mcp.git
cd youcom-mcp

  2. Установите зависимости:

    npm install

  3. Создайте файл .env на основе примера:

    cp .env.example .env

  4. Добавьте свой API-ключ You.com в файл .env :

    YOU_API_KEY=your_actual_api_key_here

  5. Создайте проект:

    npm run build

Запуск локально (необязательно)

Вы можете запустить сервер локально для тестирования:

npm start

Настройка с Клодом

Чтобы использовать этот сервер MCP с Claude (Anthropic Assistant), вам необходимо настроить Claude на использование этого сервера:

  1. Откройте настройки расширения Claude в VS Code:

    • Нажмите на значок Клода на боковой панели VS Code.

    • Нажмите на значок настроек (⚙️) и выберите «Настройки MCP».

  2. Добавьте следующую конфигурацию в раздел mcpServers :

"youcom-mcp": {
  "autoApprove": [],
  "disabled": false,
  "command": "node",
  "args": [
    "/absolute/path/to/your/youcom-mcp/dist/index.js"
  ],
  "env": {
    "YOU_API_KEY": "your_actual_api_key_here"
  },
  "transportType": "stdio"
}

Важные примечания:

  • Замените /absolute/path/to/your/youcom-mcp/dist/index.js на фактический путь в вашей системе.

  • Замените your_actual_api_key_here на ваш ключ API You.com

Примеры использования

После настройки вы сможете использовать инструменты MCP непосредственно в разговорах с Клодом:

Поиск в Интернете

<use_mcp_tool>
<server_name>youcom-mcp</server_name>
<tool_name>web_search</tool_name>
<arguments>
{
  "query": "latest research on renewable energy"
}
</arguments>
</use_mcp_tool>

Умный поиск

<use_mcp_tool>
<server_name>youcom-mcp</server_name>
<tool_name>smart_search</tool_name>
<arguments>
{
  "query": "how do quantum computers work",
  "instructions": "explain in simple terms"
}
</arguments>
</use_mcp_tool>

Исследовать

<use_mcp_tool>
<server_name>youcom-mcp</server_name>
<tool_name>research</tool_name>
<arguments>
{
  "query": "effects of climate change on ocean ecosystems",
  "instructions": "focus on coral reefs"
}
</arguments>
</use_mcp_tool>

Поиск новостей

<use_mcp_tool>
<server_name>youcom-mcp</server_name>
<tool_name>news_search</tool_name>
<arguments>
{
  "query": "latest developments in AI"
}
</arguments>
</use_mcp_tool>

Внося вклад

Вклады приветствуются! Пожалуйста, не стесняйтесь отправлять запрос на включение.

Запуск оценок

Пакет evals загружает клиент mcp, который затем запускает файл index.ts, поэтому нет необходимости перестраиваться между тестами. Вы можете загрузить переменные среды, указав префикс команды npx. Полную документацию можно найти здесь .

OPENAI_API_KEY=your-key  npx mcp-eval src/evals/evals.ts src/index.ts

Лицензия

Массачусетский технологический институт

Благодарности

В этом проекте для поиска используется API You.com .

Available Tools

4 tools
researchD
ParametersJSON Schema
NameRequiredDescriptionDefault
instructionsNoCustom instructions for tailoring the response (optional)
queryYesThe research query to send to You.com's Research API

TDQS

D1/5.0
Behavior1/5

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.

Conciseness1/5

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.

Completeness1/5

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.

Parameters1/5

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.

Purpose1/5

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.

Usage Guidelines1/5

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.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 4 tool updatesv1.0.0
    • First observednews_search
    • First observedresearch
    • First observedsmart_search
    • First observedweb_search
Deploy Server
Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

TDQS

D1.4/5.0

Scored across 4 tools

Disambiguation1/5

The tools are highly ambiguous with overlapping purposes, as all four tools appear to perform search-related functions without clear distinctions. Without descriptions, it's impossible to differentiate between 'news_search', 'research', 'smart_search', and 'web_search', making them effectively indistinguishable for an agent.

Naming Consistency3/5

The naming shows mixed conventions: 'news_search' and 'web_search' follow a consistent noun_verb pattern, but 'research' and 'smart_search' deviate with different structures. While readable, the inconsistency in verb usage and pattern reduces predictability across the set.

Tool Count3/5

With 4 tools, the count is borderline for a search-focused server, as it feels thin but not unreasonable. However, the lack of descriptions makes it hard to assess if this number adequately covers the domain, suggesting potential under-scoping or redundancy.

Completeness2/5

Inferred as a search server, there are significant gaps in coverage, such as missing filtering, sorting, or result management tools. The surface is severely incomplete for a robust search domain, likely causing agent failures due to limited operational capabilities.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

  • Kagi MCP Server by kagisearch

    Kagi MCP Serverofficial

    kagisearch
    A
    license
    A
    quality
    D
    maintenance
    An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
    2
    533
    MIT

  • Perplexity MCP Server

    RossH121
    A
    license
    A
    quality
    D
    maintenance
    An MCP server that enables Claude to perform web searches using Perplexity's API with intelligent model selection based on query intent and support for domain and recency filtering.
    6
    4
    MIT

Appeared in Searches