Skip to main content
Glama
enesjakozh
PhialsBasement

MCP Web Research Server

by PhialsBasement
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

MCP 웹 리서치 서버

웹 연구를 위한 MCP(Model Context Protocol) 서버.

클로드에 실시간 정보를 가져와 원하는 주제를 쉽게 조사해보세요.

특징

  • Google 검색 통합 --- 이 포크는 이 문제를 해결합니다 --- 이제 더 이상 CAPTCHA가 차단되지 않습니다.

  • 웹페이지 콘텐츠 추출

  • 연구 세션 추적(방문한 페이지 목록, 검색어 등)

  • 스크린샷 캡처

Related MCP server: MCP Web Research Server

필수 조건

설치

먼저, Claude Desktop 앱을 다운로드하여 설치했고 npm도 설치했는지 확인하세요.

다음으로, claude_desktop_config.json 에 이 항목을 추가합니다(Mac에서는 ~/Library/Application\ Support/Claude/claude_desktop_config.json 에 있음).

지엑스피1

이 구성을 사용하면 Claude Desktop이 필요할 때 웹 연구 MCP 서버를 자동으로 시작할 수 있습니다.

용법

Claude와 채팅을 시작하고 웹 리서치에 도움이 될 만한 메시지를 보내세요. 심층적인 웹 리서치에 맞춰 미리 만들어진 프롬프트를 원하시면 이 패키지를 통해 제공되는 agentic-research 프롬프트를 사용하실 수 있습니다. Claude 데스크톱에서 채팅 입력란의 페이퍼클립 아이콘을 클릭한 다음 Choose an integration → webresearch → agentic-research 선택하여 해당 프롬프트에 접속하세요.

도구

  1. search_google

    • Google 검색을 수행하고 결과를 추출합니다.

    • 인수: { query: string }

  2. visit_page

    • 웹 페이지를 방문하여 콘텐츠를 추출합니다.

    • 인수: { url: string, takeScreenshot?: boolean }

  3. take_screenshot

    • 현재 페이지의 스크린샷을 찍습니다.

    • 인수가 필요하지 않습니다

프롬프트

agentic-research

클로드가 철저한 웹 조사를 수행하는 데 도움이 되는 가이드 조사 프롬프트입니다. 이 프롬프트는 클로드에게 다음을 지시합니다.

  • 주제 환경을 이해하려면 광범위한 검색으로 시작하세요.

  • 고품질의 권위 있는 출처를 우선시하세요

  • 연구 결과를 바탕으로 연구 방향을 반복적으로 개선합니다.

  • 귀하에게 정보를 제공하고 대화형으로 연구를 안내합니다.

  • 항상 URL을 사용하여 출처를 인용하세요

자원

우리는 두 가지를 MCP 리소스로 공개합니다: (1) 캡처한 웹페이지 스크린샷, (2) 연구 세션.

스크린샷

스크린샷을 찍으면 MCP 리소스로 저장됩니다. Claude Desktop에서 Paperclip 아이콘을 통해 캡처한 스크린샷에 액세스할 수 있습니다.

연구 세션

서버는 다음을 포함하는 연구 세션을 유지합니다.

  • 검색어

  • 방문한 페이지

  • 추출된 콘텐츠

  • 스크린샷

  • 타임스탬프

제안

최상의 결과를 얻으려면, 조사할 때 agentic-research 프롬프트를 사용하지 않기로 했다면, 클로드가 일반적인 주제를 조사할 때 사용할 수 있는 양질의 출처를 제안하는 것이 도움이 될 수 있습니다. 예를 들어, "오늘의 뉴스" 대신 news today from reuters or AP news today 제안할 수 있습니다.

문제들

이건 알파 이전 코드에 가깝습니다. AIGC이기도 하니 버그가 있을 수 있습니다.

문제가 발생하면 Claude Desktop의 MCP 로그를 확인하는 것이 도움이 될 수 있습니다.

tail -n 20 -f ~/Library/Logs/Claude/mcp*.log

개발

# Install dependencies
pnpm install

# Build the project
pnpm build

# Watch for changes
pnpm watch

# Run in development mode
pnpm dev

요구 사항

  • 노드.js >= 18

  • Playwright(종속성으로 자동 설치됨)

검증된 플랫폼

  • [x] 맥OS

  • [x] 리눅스

  • [x] 윈도우

특허

MIT

작가

mzxrai

Available Tools

4 tools
search_googleA

Performs a web search using Google, ideal for finding current information, news, websites, and general knowledge. Use this tool when you need to research topics, find recent information, or gather data from the web. Returns structured search results with titles, URLs, and snippets.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query

TDQS

A4/5.0
Behavior3/5

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

No annotations provided, so description must cover behavioral aspects. States return format (titles, URLs, snippets) but omits details like rate limits, query length limits, pagination, or error handling. Basic transparency but with notable gaps.

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?

Three sentences, no unnecessary words, front-loaded with purpose. Every sentence adds value: what it does, when to use, what it returns.

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 a simple tool with one parameter and no output schema, the description covers primary purpose, use cases, and return format. Lacks details like result count limits or error scenarios, but adequate for basic usage.

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?

Only one parameter (query) with 100% schema description coverage (minimal: 'Search query'). The tool description adds no further parameter-specific meaning, only repeating use cases. 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?

Clearly states 'Performs a web search using Google' with specific use cases (current information, news, websites, general knowledge). Distinguishes from sibling tools like search_scholar (academic) and visit_page (browsing).

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?

Provides clear guidance on when to use: 'research topics, find recent information, or gather data from the web.' Does not explicitly mention when not to use or alternatives, but context implies a general web search tool.

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

search_scholarA

Searches Google Scholar for academic papers and scholarly articles. Use this tool when researching scientific topics, looking for peer-reviewed research, academic citations, or scholarly literature. Returns structured data including titles, authors, publication details, and citation counts. Ideal for academic research and evidence-based inquiries.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesAcademic search query

TDQS

A3.7/5.0
Behavior2/5

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

No annotations are provided, so the description should disclose behavioral traits. It only states that it returns structured data with certain fields, but does not mention whether the tool is read-only, has rate limits, requires authentication, or any side effects. This lack of transparency is a gap.

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 concise with three sentences, front-loading the core action. It is efficient and easy to parse, though slightly more structure (e.g., bullet points) could improve readability.

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 search tool with one parameter and no output schema, the description covers purpose, usage context, and return structure. However, it lacks details on pagination, result limits, or sorting, which could be useful for an agent.

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 input schema already provides a description for the only parameter ('Academic search query'). The tool description does not add any additional meaning beyond what the schema states, so baseline 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 clearly states the tool's action ('Searches Google Scholar') and specifies the resource ('academic papers and scholarly articles'). It distinguishes itself from sibling tools like search_google by focusing on academic content.

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 provides explicit guidance on when to use this tool (researching scientific topics, peer-reviewed research, etc.). It does not explicitly mention when not to use or contrast with alternatives, but the focus on academic literature implicitly differentiates it from general web searches.

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

take_screenshotA

Captures a visual image of the currently loaded webpage. Use this tool when you need to preserve visual information, analyze page layouts, or document the current state of a webpage. Perfect for situations where textual content alone doesn't convey the full context.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A3.9/5.0
Behavior2/5

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

No annotations exist, and the description lacks details about side effects, image format, or behavior if no page is loaded, leaving significant behavioral gaps.

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 efficient sentences, front-loaded with the verb 'Captures', and every word adds value without redundancy.

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?

While the purpose is clear, the description omits details about output (e.g., format, full-page vs viewport), which would help completeness for a simple tool.

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?

With zero parameters, baseline is 4; the description correctly implies no configuration is needed.

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 captures a visual image of the currently loaded webpage, and it is distinct from sibling tools like search_google, search_scholar, and visit_page.

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 provides clear use cases (preserve visual info, analyze layouts, document state) but does not explicitly mention when not to use it or alternatives, though siblings are different.

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

visit_pageA

Navigates to a specific URL and extracts the page content in readable format, with option to capture a screenshot. Use this tool to deeply analyze specific web pages, read articles, examine documentation, or verify information directly from the source. Especially useful for in-depth research after identifying relevant pages via search.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesURL to visit
takeScreenshotNoWhether to take a screenshot

TDQS

A4.4/5.0
Behavior3/5

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

No annotations provided, so description must cover behavioral traits. It mentions extracting content and screenshots but omits details like error handling, dynamic content, rate limits, or side effects.

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?

Three sentences, first covers core action and options, next two provide guidance. No unnecessary words, well-structured and front-loaded.

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 2 params and no output schema, description adequately covers purpose and usage but lacks details on output format (e.g., how page content is returned) and potential limitations.

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?

Schema coverage is 100% with adequate descriptions. Description adds context for takeScreenshot ('option to capture a screenshot') but does not clarify URL format or restrictions 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 clearly states the action (navigates to URL, extracts content, optionally screenshots) and differentiates from sibling tools like search_google (which finds pages) and take_screenshot (which only captures images).

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

Usage Guidelines5/5

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

Explicitly recommends use for in-depth research after search, and outlines scenarios (analyze pages, read articles, verify info), providing clear context for when to use.

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 updates
    • First observedsearch_google
    • First observedsearch_scholar
    • First observedtake_screenshot
    • First observedvisit_page
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: general web search vs. academic search vs. page content extraction vs. visual capture. No overlaps in functionality.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with snake_case (search_google, search_scholar, take_screenshot, visit_page), making them predictable.

Tool Count5/5

Four tools is well-scoped for a web research server—enough to cover core tasks without unnecessary complexity.

Completeness4/5

The set covers search (web and academic), page visiting, and screenshot capabilities. Missing a tool for managing search history or saving results, but core research workflows are supported.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches