MCP Google Server
mcp-google-server Google 맞춤 검색 및 웹 페이지 읽기용 MCP 서버
Google Custom Search API와 웹페이지 콘텐츠 추출 기능을 사용하여 웹 검색 기능을 제공하는 모델 컨텍스트 프로토콜 서버입니다.
설정
Google API 키 및 검색 엔진 ID 얻기
Google Cloud 프로젝트 만들기:
Google Cloud Console 로 이동
새 프로젝트를 만들거나 기존 프로젝트를 선택하세요
프로젝트에 대한 청구를 활성화하세요
사용자 정의 검색 API 활성화:
API 라이브러리 로 이동
"사용자 정의 검색 API"를 검색하세요
"활성화"를 클릭하세요
API 키 받기:
자격 증명 으로 이동
"자격 증명 만들기" > "API 키"를 클릭하세요.
API 키를 복사하세요
(선택 사항) API 키를 사용자 지정 검색 API로만 제한합니다.
사용자 정의 검색 엔진 만들기:
프로그래밍 가능한 검색 엔진 으로 이동
검색하려는 사이트를 입력하세요(일반 웹 검색의 경우 www.google.com을 사용하세요)
"만들기"를 클릭하세요
다음 페이지에서 "사용자 정의"를 클릭하세요.
설정에서 "전체 웹 검색"을 활성화하세요.
검색 엔진 ID(cx)를 복사하세요
Related MCP server: MCP Server for Google Search
개발
종속성 설치:
지엑스피1
서버를 빌드하세요:
npm run build자동 재빌드를 사용한 개발의 경우:
npm run watch특징
검색 도구
Google 맞춤 검색 API를 사용하여 웹 검색을 수행합니다.
전체 웹 또는 특정 사이트 검색
결과의 제어 번호(1-10)
제목, 링크 및 스니펫을 사용하여 구조화된 결과를 얻으세요
웹페이지 리더 도구
모든 웹 페이지에서 콘텐츠 추출:
웹 페이지 콘텐츠 가져오기 및 구문 분석
페이지 제목과 본문 추출
스크립트와 스타일을 제거하여 콘텐츠를 정리합니다.
제목, 텍스트 및 URL을 포함한 구조화된 데이터 반환
설치
Smithery를 통해 설치
Smithery 를 통해 Claude Desktop에 Google 맞춤 검색 서버를 자동으로 설치하는 방법:
npx -y @smithery/cli install @adenot/mcp-google-search --client claudeClaude Desktop과 함께 사용하려면 Google API 자격 증명으로 서버 구성을 추가하세요.
MacOS의 경우: ~/Library/Application Support/Claude/claude_desktop_config.json Windows의 경우: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"google-search": {
"command": "npx",
"args": [
"-y",
"@adenot/mcp-google-search"
],
"env": {
"GOOGLE_API_KEY": "your-api-key-here",
"GOOGLE_SEARCH_ENGINE_ID": "your-search-engine-id-here"
}
}
}
}용법
검색 도구
{
"name": "search",
"arguments": {
"query": "your search query",
"num": 5 // optional, default is 5, max is 10
}
}웹페이지 리더 도구
{
"name": "read_webpage",
"arguments": {
"url": "https://example.com"
}
}웹 페이지 리더의 응답 예:
{
"title": "Example Domain",
"text": "Extracted and cleaned webpage content...",
"url": "https://example.com"
}디버깅
MCP 서버는 stdio를 통해 통신하므로 디버깅이 어려울 수 있습니다. 패키지 스크립트로 제공되는 MCP Inspector를 사용하는 것이 좋습니다.
npm run inspector검사기는 브라우저에서 디버깅 도구에 액세스할 수 있는 URL을 제공합니다.
Available Tools
2 toolsread_webpageA
Fetch and extract text content from a webpage
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL of the webpage to read |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral traits. It only states basic purpose without mentioning rate limits, authentication, dynamic content handling, or error responses.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with action, no unnecessary words. Perfectly concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description is adequate but lacks details on handling of large pages, timeouts, or what 'text content' entails (e.g., stripping HTML).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (single 'url' parameter described), so baseline is 3. The description adds no extra meaning beyond the schema, such as URL format or protocol support.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action ('Fetch and extract') and the resource ('text content from a webpage'), distinguishing it from sibling tool 'search' which is for querying.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. The sibling 'search' suggests a different purpose, but the description does not clarify contexts or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
searchC
Perform a web search query
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query | |
| num | No | Number of results (1-10) |
TDQS
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 only states the action, omitting details such as result format, rate limits, data sources, or any side effects. This is insufficient for a tool with no structural safety hints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, straightforward sentence with no extraneous information. 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.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no output schema and no annotations, the description is too minimal to be considered complete. It does not address limitations, result handling, or how to interpret outputs, leaving gaps for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for both parameters (100% coverage). The description adds no additional meaning beyond what the schema offers, so a baseline score of 3 is appropriate per the guidelines.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Perform a web search query' clearly states the action and resource, but does not differentiate from the sibling tool 'read_webpage', which likely fetches content from a single URL. A more specific purpose, such as indicating it searches the entire web, would improve clarity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus the sibling tool 'read_webpage'. There is no mention of when a web search is appropriate or when to avoid it, leaving the agent without decision-making 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.
2 tool updates
v1.0.0- First observed
read_webpage - First observed
search
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: one fetches content from a specific URL, the other performs web searches. There is no overlap or ambiguity.
The naming pattern is inconsistent: 'read_webpage' uses verb_noun with an underscore, while 'search' is a single verb without a noun or underscore. This lack of uniformity could confuse agents.
With only 2 tools, the server is minimal but still covers two core web operations. The count is at the low end of what's reasonable for a focused server, but not necessarily inappropriate.
The set provides basic web search and page reading, which covers common use cases. However, it lacks features like filtering search results, handling pagination, or extracting specific elements, leaving minor gaps.
Maintenance
Related MCP Connectors
Provides AI assistants with access to Seltz's powerful Web Search capabilities.
1 Google Search endpoints. Pay per call in USDC via x402.
Search Google straight from your AI agent. Web results, images, videos, news, products, scholarly ar
Google search, news, maps, scholar and public webpages for AI agents, with Markdown results.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables LLMs to perform web searches using Google's Custom Search API through a standardized interface.147MIT
- FlicenseAqualityCmaintenanceA Model Context Protocol server that provides web search capabilities using Google Custom Search API and webpage content extraction functionality.26 npm2-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables AI assistants to perform web searches using Google Search API, returning up to 20 search results in JSON format.2Apache 2.0
- AlicenseBqualityDmaintenanceA Model Context Protocol server that provides web search capabilities using Google Custom Search API and webpage content extraction functionality.2MIT