de en es ja ko ru zh

SearchAPI MCP Server

Name: SearchAPI MCP Server
Author: mrgoonie

by mrgoonie

Overview Schema Source Related Servers Discussions Admin

TypeScript

Hybrid

SearchAPI.site - MCP-сервер

Этот проект предоставляет сервер Model Context Protocol (MCP), который подключает помощников на базе искусственного интеллекта к внешним источникам данных (Google, Bing и т. д.) через SearchAPI.site .

Доступные платформы

[x] Google — поиск в Интернете
[x] Google - Поиск изображений
[x] Google - Поиск YouTube
[ ] Google - Поиск на Картах
[x] Bing — поиск в Интернете
[ ] Bing — Поиск изображений
[ ] Реддит
[ ] X/Твиттер
[ ] Поиск в Facebook
[ ] Поиск группы Facebook
[ ] Инстаграм
[ ] ТикТок

SearchAPI.site

Веб-сайт
API-документы
Конфигурация пользовательского интерфейса Swagger
Создайте ключ API поиска здесь
GitHub

Related MCP server: WebSearch-MCP

Поддерживаемые транспорты

[x] "stdio" transport — транспорт по умолчанию для использования CLI
[x] Транспорт«Streamable HTTP» — для веб-клиентов
- [ ] Реализовать аутентификацию (заголовки «Authorization» с Bearer <token> )
[ ] ~~"sse" транспорт~~ (Устаревшее)
[ ] Написать тесты

Как использовать

CLI

# Google search via CLI
npm run dev:cli -- search-google --query "your search query" --api-key "your-api-key"

# Google image search via CLI
npm run dev:cli -- search-google-images --query "your search query" --api-key "your-api-key"

# YouTube search via CLI
npm run dev:cli -- search-youtube --query "your search query" --api-key "your-api-key" --max-results 5

Настройка МКП

Для локальной конфигурации с транспортом stdio:

{
  "mcpServers": {
    "searchapi": {
      "command": "node",
      "args": ["/path/to/searchapi-mcp-server/dist/index.js"],
      "transportType": "stdio"
    }
  }
}

Для удаленной конфигурации HTTP:

{
  "mcpServers": {
    "searchapi": {
      "type": "http",
      "url": "http://mcp.searchapi.site/mcp"
    }
  }
}

Переменные среды для HTTP-транспорта:

Вы можете настроить HTTP-сервер, используя следующие переменные среды:

MCP_HTTP_HOST : Хост для привязки (по умолчанию: 127.0.0.1 )
MCP_HTTP_PORT : Порт для прослушивания (по умолчанию: 8080 )
MCP_HTTP_PATH : Путь к конечной точке (по умолчанию: /mcp )

Обзор исходного кода

Что такое МКП?

Model Context Protocol (MCP) — открытый стандарт, позволяющий системам искусственного интеллекта безопасно и контекстно подключаться к внешним инструментам и источникам данных.

Этот шаблон реализует спецификацию MCP с помощью чистой многоуровневой архитектуры, которую можно расширить для создания пользовательских серверов MCP для любого API или источника данных.

Зачем использовать этот шаблон?

Архитектура, готовая к производству : следует той же схеме, которая используется в опубликованных серверах MCP, с четким разделением между CLI, инструментами, контроллерами и службами.
Безопасность типов : создано с использованием TypeScript для улучшения опыта разработки, качества кода и удобства обслуживания.
Рабочий пример : включает в себя полностью реализованный инструмент поиска IP-адресов, демонстрирующий полную модель от CLI до интеграции API.
Тестовая среда : поставляется с тестовой инфраструктурой для модульных и интеграционных тестов CLI, включая отчеты о покрытии.
Инструменты разработки : включают ESLint, Prettier, TypeScript и другие качественные инструменты, предварительно настроенные для разработки сервера MCP.

Начиная

Предпосылки

Node.js (>=18.x): Загрузить
Git : для контроля версий

Шаг 1: Клонирование и установка

# Clone the repository
git clone https://github.com/mrgoonie/searchapi-mcp-server.git
cd searchapi-mcp-server

# Install dependencies
npm install

Шаг 2: Запуск сервера разработки

Запустите сервер в режиме разработки с использованием транспорта stdio (по умолчанию):

npm run dev:server

Или с помощью потокового HTTP-транспорта:

npm run dev:server:http

Это запустит сервер MCP с горячей перезагрузкой и включит MCP Inspector по адресу http://localhost:5173 .

⚙️ Прокси-сервер прослушивает порт 6277 🔍 MCP Inspector запущен и работает по адресу http://127.0.0.1:6274

При использовании HTTP-транспорта сервер по умолчанию будет доступен по адресу http://127.0.0.1:8080/mcp .

Шаг 3: протестируйте пример инструмента

Запустите пример инструмента поиска IP-адресов из CLI:

# Using CLI in development mode
npm run dev:cli -- search-google --query "your search query" --api-key "your-api-key"

# Or with a specific IP
npm run dev:cli -- search-google --query "your search query" --api-key "your-api-key" --limit 10 --offset 0 --sort "date:d" --from_date "2023-01-01" --to_date "2023-12-31"

Архитектура

Этот шаблон следует четкой, многоуровневой архитектурной модели, которая разделяет проблемы и способствует удобству обслуживания.

Структура проекта

src/
├── cli/              # Command-line interfaces
├── controllers/      # Business logic
├── resources/        # MCP resources: expose data and content from your servers to LLMs
├── services/         # External API interactions
├── tools/            # MCP tool definitions
├── types/            # Type definitions
├── utils/            # Shared utilities
└── index.ts          # Entry point

Уровни и обязанности

Уровень CLI ( `src/cli/*.cli.ts` )

Цель : определение интерфейсов командной строки, которые анализируют аргументы и вызывают контроллеры.
Именование : Файлы должны называться <feature>.cli.ts
Тестирование : тесты интеграции CLI в <feature>.cli.test.ts

Слой инструментов ( `src/tools/*.tool.ts` )

Цель : Определить инструменты MCP со схемами и описаниями для помощников ИИ.
Именование : файлы должны иметь имена <feature>.tool.ts с типами в <feature>.types.ts
Шаблон : Каждый инструмент должен использовать zod для проверки аргументов.

Уровень контроллеров ( `src/controllers/*.controller.ts` )

Цель : Реализация бизнес-логики, обработка ошибок и форматирование ответов.
Именование : Файлы должны называться <feature>.controller.ts
Шаблон : Должен возвращать стандартизированные объекты ControllerResponse

Уровень служб ( `src/services/*.service.ts` )

Цель : Взаимодействие с внешними API или источниками данных.
Именование : Файлы должны называться <feature>.service.ts
Шаблон : чистое взаимодействие API с минимальной логикой

Уровень утилит ( `src/utils/*.util.ts` )

Цель : Обеспечить общую функциональность для всего приложения.
Ключевые возможности :
- logger.util.ts : Структурированное ведение журнала
- error.util.ts : Обработка ошибок и стандартизация
- formatter.util.ts : Помощники форматирования Markdown

Руководство по разработке

Сценарии разработки

# Start server in development mode (hot-reload & inspector)
npm run dev:server

# Run CLI in development mode
npm run dev:cli -- [command] [args]

# Build the project
npm run build

# Start server in production mode
npm run start:server

# Run CLI in production mode
npm run start:cli -- [command] [args]

Тестирование

# Run all tests
npm test

# Run specific tests
npm test -- src/path/to/test.ts

# Generate test coverage report
npm run test:coverage

оценки

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/tools/searchapi.tool.ts

Качество кода

# Lint code
npm run lint

# Format code with Prettier
npm run format

# Check types
npm run typecheck

Создание пользовательских инструментов

Чтобы добавить собственные инструменты на сервер, выполните следующие действия:

1. Определите уровень обслуживания

Создайте новую службу в src/services/ для взаимодействия с вашим внешним API:

// src/services/example.service.ts
import { Logger } from '../utils/logger.util.js';

const logger = Logger.forContext('services/example.service.ts');

export async function getData(param: string): Promise<any> {
	logger.debug('Getting data', { param });
	// API interaction code here
	return { result: 'example data' };
}

2. Создать контроллер

Добавьте контроллер в src/controllers/ для обработки бизнес-логики:

// src/controllers/example.controller.ts
import { Logger } from '../utils/logger.util.js';
import * as exampleService from '../services/example.service.js';
import { formatMarkdown } from '../utils/formatter.util.js';
import { handleControllerError } from '../utils/error-handler.util.js';
import { ControllerResponse } from '../types/common.types.js';

const logger = Logger.forContext('controllers/example.controller.ts');

export interface GetDataOptions {
	param?: string;
}

export async function getData(
	options: GetDataOptions = {},
): Promise<ControllerResponse> {
	try {
		logger.debug('Getting data with options', options);

		const data = await exampleService.getData(options.param || 'default');

		const content = formatMarkdown(data);

		return { content };
	} catch (error) {
		throw handleControllerError(error, {
			entityType: 'ExampleData',
			operation: 'getData',
			source: 'controllers/example.controller.ts',
		});
	}
}

3. Внедрение инструмента MCP

Создайте определение инструмента в src/tools/ :

// src/tools/example.tool.ts
import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
import { z } from 'zod';
import { Logger } from '../utils/logger.util.js';
import { formatErrorForMcpTool } from '../utils/error.util.js';
import * as exampleController from '../controllers/example.controller.js';

const logger = Logger.forContext('tools/example.tool.ts');

const GetDataArgs = z.object({
	param: z.string().optional().describe('Optional parameter'),
});

type GetDataArgsType = z.infer<typeof GetDataArgs>;

async function handleGetData(args: GetDataArgsType) {
	try {
		logger.debug('Tool get_data called', args);

		const result = await exampleController.getData({
			param: args.param,
		});

		return {
			content: [{ type: 'text' as const, text: result.content }],
		};
	} catch (error) {
		logger.error('Tool get_data failed', error);
		return formatErrorForMcpTool(error);
	}
}

export function register(server: McpServer) {
	server.tool(
		'get_data',
		`Gets data from the example API, optionally using \`param\`.
Use this to fetch example data. Returns formatted data as Markdown.`,
		GetDataArgs.shape,
		handleGetData,
	);
}

4. Добавить поддержку CLI

Создайте команду CLI в src/cli/ :

// src/cli/example.cli.ts
import { program } from 'commander';
import { Logger } from '../utils/logger.util.js';
import * as exampleController from '../controllers/example.controller.js';
import { handleCliError } from '../utils/error-handler.util.js';

const logger = Logger.forContext('cli/example.cli.ts');

program
	.command('get-data')
	.description('Get example data')
	.option('--param <value>', 'Optional parameter')
	.action(async (options) => {
		try {
			logger.debug('CLI get-data called', options);

			const result = await exampleController.getData({
				param: options.param,
			});

			console.log(result.content);
		} catch (error) {
			handleCliError(error);
		}
	});

5. Регистрация компонентов

Обновите точки входа для регистрации новых компонентов:

// In src/cli/index.ts
import '../cli/example.cli.js';

// In src/index.ts (for the tool)
import exampleTool from './tools/example.tool.js';
// Then in registerTools function:
exampleTool.register(server);

Инструменты отладки

Инспектор МКП

Получите доступ к визуальному инспектору MCP, чтобы протестировать свои инструменты и просмотреть сведения о запросах/ответах:

Запустите npm run dev:server
Откройте http://localhost:5173 в вашем браузере.
Тестируйте свои инструменты и просматривайте журналы прямо в пользовательском интерфейсе

Журналы сервера

Включить журналы отладки для разработки:

# Set environment variable
DEBUG=true npm run dev:server

# Or configure in ~/.mcp/configs.json

Публикация вашего MCP-сервера

Когда вы будете готовы опубликовать свой собственный сервер MCP:

Обновите package.json, указав свои данные.
Обновите README.md документацией по вашему инструменту.
Соберите проект: npm run build
Протестируйте производственную сборку: npm run start:server
Опубликовать в npm: npm publish

Лицензия

Лицензия ISC

{
	"searchapi": {
		"environments": {
			"DEBUG": "true",
			"SEARCHAPI_API_KEY": "value"
		}
	}
}

Примечание: Для обратной совместимости сервер также распознает конфигурации под полным именем пакета ( searchapi-mcp-server ) или именем пакета без области действия ( searchapi-mcp-server ), если ключ searchapi не найден. Однако для новых конфигураций рекомендуется использовать короткий ключ searchapi .

Available Tools

3 tools

search_googleC

Performs a Google search using SearchAPI.site. Requires a search "query" string, can be able to search multiple keywords that separated by commas. Returns formatted search results including titles, snippets, and links.

ParametersJSON Schema

Name	Required	Description
`query`	Yes	The search query to perform
`limit`	No	Maximum number of results to return (1-100)
`offset`	No	Offset for pagination
`sort`	No	Sort order (e.g., "date:d" for newest first)
`from_date`	No	Start date for filtering results (format: YYYY-MM-DD)
`to_date`	No	End date for filtering results (format: YYYY-MM-DD)

TDQS

C2.8/5.0

Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It states the tool 'Returns formatted search results including titles, snippets, and links,' which gives some output context, but lacks critical behavioral details like rate limits, authentication requirements, error handling, pagination behavior (beyond the offset parameter), or whether this is a read-only operation. The mention of 'SearchAPI.site' hints at a third-party service but doesn't explain implications.

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

Conciseness3/5

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

The description is reasonably concise with three sentences, but it's not optimally front-loaded. The first sentence states the purpose, but the second sentence awkwardly mixes parameter guidance ('Requires a search "query" string') with feature description ('can be able to search multiple keywords'). The third sentence covers return values. Some redundancy exists (e.g., 'query' is mentioned twice), and the structure could be tighter for better clarity.

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

Completeness2/5

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

Given no annotations, no output schema, and 6 parameters (though well-documented in schema), the description is incomplete. It lacks behavioral context (e.g., rate limits, auth), doesn't explain the relationship with sibling tools, and provides minimal guidance on usage. For a search tool with multiple parameters and no structured output definition, more contextual information would be helpful for an AI agent to use it effectively.

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%, so the schema already documents all 6 parameters thoroughly. The description adds minimal value beyond the schema: it mentions the query parameter and that it 'can be able to search multiple keywords that separated by commas' (though awkwardly phrased), but doesn't explain other parameters like limit, offset, sort, from_date, or to_date. Baseline 3 is appropriate when schema does the heavy lifting.

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 'Performs a Google search using SearchAPI.site' with a specific verb ('Performs') and resource ('Google search'), distinguishing it from sibling tools like search_google_images and search_youtube by focusing on general web search. However, it doesn't explicitly contrast with siblings beyond the different search types.

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

Usage Guidelines2/5

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 like search_google_images or search_youtube. It mentions the tool can search multiple keywords separated by commas, but this is more about parameter usage than contextual guidance. No explicit when/when-not instructions or alternative recommendations are included.

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

search_google_imagesB

Performs a Google image search using SearchAPI.site. Requires a search query and your SearchAPI.site API key. Returns formatted image search results including titles, thumbnails, and source links.

ParametersJSON Schema

Name	Required	Description
`query`	Yes	The image search query to perform
`limit`	No	Maximum number of results to return (1-100)
`offset`	No	Offset for pagination
`sort`	No	Sort order (e.g., "date:d" for newest first)
`from_date`	No	Start date for filtering results (format: YYYY-MM-DD)
`to_date`	No	End date for filtering results (format: YYYY-MM-DD)

TDQS

B3.2/5.0

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 of behavioral disclosure. It mentions the API key requirement (authentication need) and describes the return format ('formatted image search results including titles, thumbnails, and source links'), which adds value beyond the input schema. However, it doesn't mention rate limits, error conditions, or other behavioral traits like whether results are cached or real-time.

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

Conciseness4/5

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

The description is appropriately sized with three concise sentences that each add value: what it does, what it requires, and what it returns. It's front-loaded with the core purpose. There's minimal waste, though it could be slightly more structured with bullet points for the three key pieces of information.

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?

For a tool with 6 parameters, 100% schema coverage, but no annotations and no output schema, the description provides adequate but incomplete context. It covers the purpose, authentication requirement, and return format, but doesn't address error handling, rate limits, or provide examples. The absence of an output schema means the description's mention of return format is helpful but could be more detailed.

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%, so the schema already documents all 6 parameters thoroughly. The description adds no additional parameter semantics beyond what's in the schema - it mentions 'search query' and 'API key' but doesn't explain parameter interactions, defaults, or usage examples. Baseline 3 is appropriate when the schema does the heavy lifting.

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 'performs a Google image search using SearchAPI.site' which is a specific verb+resource combination. It distinguishes itself from sibling tools like 'search_google' and 'search_youtube' by specifying it's for images, though it doesn't explicitly contrast with them in the description text itself.

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

Usage Guidelines2/5

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

The description mentions the requirement for a SearchAPI.site API key, which provides some usage context. However, it offers no guidance on when to use this tool versus the sibling tools (search_google, search_youtube) or any alternatives. There's no explicit 'when' or 'when not' guidance.

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

search_youtubeB

Performs a YouTube search using SearchAPI.site. Requires a search query and your SearchAPI.site API key. Returns formatted YouTube search results including video titles, thumbnails, descriptions, and links. Supports optional parameters for pagination, sorting, filtering by date and duration.

ParametersJSON Schema

Name	Required	Description
`query`	Yes	The YouTube search query to perform
`maxResults`	No	Maximum number of results to return (1-50)
`pageToken`	No	Token for pagination to get next/previous page of results
`order`	No	Sort order for results
`publishedAfter`	No	Number of days to filter videos from
`videoDuration`	No	Filter by video duration

TDQS

B3.4/5.0

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 of behavioral disclosure. It mentions the API key requirement (auth needs) and describes the return format (video titles, thumbnails, descriptions, links), which adds value beyond the input schema. However, it doesn't cover rate limits, error handling, or other operational constraints.

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

Conciseness4/5

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

The description is appropriately sized with four sentences that each add value: purpose, requirements, returns, and optional features. It's front-loaded with core functionality. Minor improvement could come from tighter phrasing, but there's no wasted content.

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?

For a search tool with 6 parameters, 100% schema coverage, and no output schema, the description provides adequate context on what the tool does and returns. However, without annotations or output schema, it lacks details on response structure, error cases, or performance characteristics that would help an agent use it effectively.

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%, so the schema already documents all 6 parameters thoroughly. The description adds minimal value by listing optional parameters (pagination, sorting, filtering by date and duration) but doesn't provide additional syntax, format, or usage details beyond what's in the schema. This meets the baseline for high schema coverage.

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 specific action ('Performs a YouTube search') and resource ('using SearchAPI.site'), distinguishing it from sibling tools like search_google and search_google_images by specifying YouTube as the search target. It provides a complete verb+resource+scope combination.

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

Usage Guidelines2/5

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

The description mentions when to use this tool (for YouTube searches) but provides no guidance on when to choose it versus the sibling tools search_google or search_google_images. There's no explicit comparison or exclusion criteria, leaving the agent to infer usage context.

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.

3 tool updatesAug 14, 2025
- First observedsearch_google
- First observedsearch_google_images
- First observedsearch_youtube

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

B3.4/5.0

Scored 2026-04-18 10:15 across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose targeting a specific search type: Google web search, Google image search, and YouTube search. The descriptions explicitly differentiate them by platform and result format, with no overlap in functionality that could cause confusion.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern with 'search_' prefix followed by the target platform (google, google_images, youtube). This predictable naming scheme makes it easy for agents to understand and select the appropriate tool.

Tool Count4/5

Three tools is reasonable for a search API server, covering major search platforms. However, it feels slightly thin—adding tools for other platforms (like news or shopping search) could make it more comprehensive, but the current count is appropriate for the core functionality.

Completeness4/5

The toolset covers the essential search operations for Google web, images, and YouTube, which aligns well with the server's purpose. A minor gap is the lack of a general search tool that could handle other platforms or unified search, but agents can work effectively with the provided tools.

Maintenance

ActivityInactive

ResponsivenessUnresponsive

Resources

Need Help?

Related Servers

Related MCP Connectors

SSearch B
cc.ssearch
Free web search for AI agents. No API key required. Hosted MCP in active development.
Search Browser Automation
81
pixserp A
com.pixserp
Live AI-native web search with citations. One tool for every MCP client. Flat per-request pricing.
Search Browser Automation
12
MESSORA A
dev.messora
Scrape, crawl and search the web for AI agents via MCP.
Web Scraping Browser Automation Search
1
AIsa Web Search & Research AOAuth
one.aisa
Your agent needs the open web — searched by more than one engine, and read as clean markdown rather than raw HTML. **What you can ask for** • "Search this question with two providers and tell me where they disagree." • "Scrape these 40 URLs into markdown, in one batch." • "Crawl this documentation site and give me every page." • "Do deep research on this topic and cite the sources." • "Find the academic papers behind this claim." **How to use it** Point any MCP client at https://mcp.aisa.one/search/mcp and sign in with OAuth — there is no key to create or paste. 30 tools across several independent providers: Tavily and Exa search, answers, contents and agent runs; Firecrawl scrape, batch scrape, crawl, map and search; Perplexity Sonar, Sonar Pro, reasoning and deep research; Oxylabs AI search and LLM jobs; OpenAI and Anthropic web search; and scholarly search. **Why this rather than the source** Several independent indexes behind one account, because one engine's blind spot is not visible from inside it. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Find the page here, then ask the same agent who links to it or how much traffic it gets — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** https://mcp.aisa.one/seo-serp/mcp for the Google results page itself, https://mcp.aisa.one/seo-serp-other-engines/mcp for Bing, Baidu and Naver.
Browser Automation Search Web Scraping
351

Related MCP Servers

MCP Server
RAG Systems Databases File Systems
GobinFan
F
license
B
quality
D
maintenance
Implements the Model Context Protocol (MCP) to provide AI models with a standardized interface for connecting to external data sources and tools like file systems, databases, or APIs.
Updated a year ago (2025-05-05 08:18 UTC)
1
153
-
WebSearch-MCP
Search Web Scraping RAG Systems
mnhlt
A
license
B
quality
C
maintenance
A Model Context Protocol server that enables AI assistants to perform real-time web searches, retrieving up-to-date information from the internet via a Crawler API.
Updated a year ago (2025-04-30 18:04 UTC)
1
44 npm
42
ISC
SearchAPI MCP Server
Search Travel & Transportation
lianshuang-photo
A
license
D
quality
D
maintenance
Model Context Protocol server that enables AI assistants like Claude to access searchapi.io API for searching Google Maps, flights, hotels, and other web information.
Updated a year ago (2025-06-02 15:37 UTC)
9
12 npm
MIT
WebQuest MCP
Browser Automation Web Scraping
mustafametesengul
A
license
Not graded
quality
C
maintenance
A Model Context Protocol server that exposes powerful web search and scraping tools to AI agents and MCP-compatible clients.
Updated 8 months ago (2026-02-12 20:56 UTC)
Apache 2.0

SearchAPI.site - MCP-сервер

Доступные платформы

SearchAPI.site

Поддерживаемые транспорты

Как использовать

CLI

Настройка МКП

Обзор исходного кода

Что такое МКП?

Зачем использовать этот шаблон?

Начиная

Предпосылки

Шаг 1: Клонирование и установка

Шаг 2: Запуск сервера разработки

Шаг 3: протестируйте пример инструмента

Архитектура

Структура проекта

Уровни и обязанности

Уровень CLI ( src/cli/*.cli.ts )

Слой инструментов ( src/tools/*.tool.ts )

Уровень контроллеров ( src/controllers/*.controller.ts )

Уровень служб ( src/services/*.service.ts )

Уровень утилит ( src/utils/*.util.ts )

Руководство по разработке

Сценарии разработки

Тестирование

оценки

Качество кода

Создание пользовательских инструментов

1. Определите уровень обслуживания

2. Создать контроллер

3. Внедрение инструмента MCP

4. Добавить поддержку CLI

5. Регистрация компонентов

Инструменты отладки

Инспектор МКП

Журналы сервера

Публикация вашего MCP-сервера

Лицензия

Available Tools

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches

Уровень CLI ( `src/cli/*.cli.ts` )

Слой инструментов ( `src/tools/*.tool.ts` )

Уровень контроллеров ( `src/controllers/*.controller.ts` )

Уровень служб ( `src/services/*.service.ts` )

Уровень утилит ( `src/utils/*.util.ts` )