모델 컨텍스트 프로토콜(MCP) 서버를 통해 클로드와 같은 AI 비서가 Exa AI Search API를 사용하여 웹 검색을 수행할 수 있습니다. 이 설정을 통해 AI 모델은 안전하고 통제된 방식으로 실시간 웹 정보를 얻을 수 있습니다.
데모 영상 https://www.loom.com/share/ac676f29664e4c6cb33a2f0a63772038?sid=0e72619f-5bfc-415d-a705-63d326373f60
모델 컨텍스트 프로토콜(MCP)은 Claude Desktop과 같은 AI 앱이 외부 도구 및 데이터 소스에 연결할 수 있도록 하는 시스템입니다. AI 어시스턴트가 사용자의 제어권을 유지하면서 로컬 서비스 및 API를 사용할 수 있는 명확하고 안전한 방법을 제공합니다.
Related MCP server: Perplexity MCP Server
Exa MCP 서버:
Exa의 강력한 검색 API를 사용하여 AI 도우미가 웹 검색을 수행할 수 있도록 합니다.
제목, URL, 콘텐츠 스니펫을 포함한 구조화된 검색 결과를 제공합니다.
최근 검색 내용을 참조용 리소스로 캐시합니다.
속도 제한 및 오류 사례를 정상적으로 처리합니다.
최신 콘텐츠에 대한 실시간 웹 크롤링을 지원합니다.
시작하기 전에 다음 사항을 확인하세요.
Node.js (v18 이상)
Claude Desktop 설치됨
Git 설치됨
다음을 실행하여 Node.js 설치를 확인할 수 있습니다.
지엑스피1
npm install -g exa-mcp-serverSmithery를 통해 Claude Desktop용 Exa MCP 서버를 자동으로 설치하려면:
npx -y @smithery/cli install exa --client claude저장소를 복제합니다.
git clone https://github.com/exa-labs/exa-mcp-server.git
cd exa-mcp-server종속성 설치:
npm install프로젝트를 빌드하세요:
npm run build글로벌 링크를 만듭니다(이렇게 하면 서버를 어디서나 실행할 수 있습니다):
npm linkClaude Desktop 앱 설정 내부에서 claude_desktop_config.json을 찾을 수 있습니다.
Claude Desktop 앱을 열고 왼쪽 상단 메뉴 표시줄에서 개발자 모드를 활성화하세요.
활성화되면 설정(왼쪽 상단 메뉴 표시줄에서도 가능)을 열고 개발자 옵션으로 이동하면 '구성 편집' 버튼이 있습니다. 이 버튼을 클릭하면 claude_desktop_config.json 파일이 열리고 필요한 편집 작업을 할 수 있습니다.
또는 (터미널에서 claude_desktop_config.json을 열려는 경우)
Claude Desktop 구성을 엽니다.
code ~/Library/Application\ Support/Claude/claude_desktop_config.jsonClaude Desktop 구성을 엽니다.
code %APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": {
"exa": {
"command": "npx",
"args": ["/path/to/exa-mcp-server/build/index.js"],
"env": {
"EXA_API_KEY": "your-api-key-here"
}
}
}
}your-api-key-here dashboard.exa.ai/api-keys 의 실제 Exa API 키로 바꾸세요.
변경 사항을 적용하려면 다음을 수행하세요.
Claude Desktop을 완전히 종료합니다(창을 닫는 것만이 아닙니다)
Claude Desktop을 다시 시작하세요
Exa 서버가 연결되었는지 확인하려면 🔌 아이콘을 찾으세요.
설정이 완료되면 Claude에게 웹 검색을 요청하세요. 다음은 몇 가지 프롬프트 예시입니다.
Can you search for recent developments in quantum computing?Search for and summarize the latest news about artificial intelligence startups in new york.Find and analyze recent research papers about climate change solutions.Search for today's breaking news about tech.Search for the top 10 AI research papers from 2023, and only use live crawling as a fallback.Search for electric vehicles and return 3 results, always using live crawling.서버는 다음을 수행합니다.
검색 요청을 처리합니다
최적의 설정(라이브 크롤링 포함)으로 Exa API 쿼리
Claude에게 포맷된 결과를 반환합니다.
나중에 참조할 수 있도록 검색 내용을 캐시합니다.
간소화된 웹 검색 도구 : Claude가 쿼리 매개변수만으로 웹을 검색할 수 있도록 합니다.
사용자 정의 가능한 검색 매개변수 : 결과 수와 라이브 크롤링 전략을 제어합니다.
자동 라이브 크롤링 : 지정된 전략에 따라 실시간 크롤링을 사용합니다.
사전 설정 최적 매개변수 : 결과 수 및 문자 제한에 대한 최상의 기본값을 사용합니다.
검색 캐싱 : 최근 검색 내용을 참조용 리소스로 저장합니다.
오류 처리 : API 오류 및 속도 제한을 우아하게 처리합니다.
유형 안전성 : Zod 검증을 통한 전체 TypeScript 구현
MCP 준수 : 최신 MCP 프로토콜 사양을 완벽하게 구현합니다.
MCP Inspector를 사용하여 서버를 직접 테스트할 수 있습니다.
npx @modelcontextprotocol/inspector node ./build/index.js이렇게 하면 서버의 기능을 탐색하고, 검색 쿼리를 실행하고, 캐시된 검색 결과를 볼 수 있는 대화형 인터페이스가 열립니다.
서버를 찾을 수 없습니다
npm 링크가 올바르게 설정되었는지 확인하세요
Claude Desktop 구성 구문 확인
Node.js가 제대로 설치되었는지 확인하세요
API 키 문제
EXA_API_KEY가 유효한지 확인하세요
Claude Desktop 구성에서 EXA_API_KEY가 올바르게 설정되었는지 확인하세요.
API 키 주위에 공백이나 따옴표가 없는지 확인하세요.
연결 문제
Claude Desktop을 완전히 다시 시작하세요
Claude Desktop 로그 확인: GXP18
문제가 발생하면 MCP 문서를 검토하거나 GitHub 토론을 방문하여 커뮤니티 지원을 받으세요.
강력한 검색 API를 제공하는 Exa AI
MCP 사양을 위한 모델 컨텍스트 프로토콜
클로드 데스크탑을 위한 인류학
Search and get relevant context for any programming task. Exa-code has the highest quality and freshest context for libraries, SDKs, and APIs. Use this tool for ANY question or task for related to programming. RULE: when the user's query contains exa-code or anything related to code, you MUST use this tool.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query to find relevant context for APIs, Libraries, and SDKs. For example, 'React useState hook examples', 'Python pandas dataframe filtering', 'Express.js middleware', 'Next js partial prerendering configuration' | |
| tokensNum | No | Number of tokens to return (1000-50000). Default is 5000 tokens. Adjust this value based on how much context you need - use lower values for focused queries and higher values for comprehensive documentation. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds value by emphasizing 'highest quality and freshest context' and the programming domain focus, but doesn't disclose additional behavioral traits like rate limits, authentication needs, or response format details. No contradiction with annotations exists.
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 front-loaded with the core purpose and usage rule, but includes some redundancy (e.g., repeating 'exa-code' emphasis). Sentences are generally purposeful, though the 'RULE' phrasing could be more integrated. Overall efficient but with minor verbosity.
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's moderate complexity (2 parameters, no output schema), annotations cover safety aspects, and the description provides clear purpose and usage rules. However, it lacks details on response structure or error handling, which would enhance completeness for a search tool.
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 description coverage is 100%, providing full documentation for both parameters. The description doesn't add meaningful parameter semantics beyond what's in the schema, such as explaining query formulation strategies or token usage trade-offs. Baseline score of 3 is appropriate given the comprehensive schema.
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 clearly states the tool's purpose: 'Search and get relevant context for any programming task' with specific focus on 'libraries, SDKs, and APIs.' It distinguishes from the sibling tool 'web_search_exa' by specifying programming-related content, though it doesn't explicitly contrast their differences beyond domain focus.
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 explicit usage guidance: 'Use this tool for ANY question or task related to programming' and includes a mandatory rule: 'when the user's query contains exa-code or anything related to code, you MUST use this tool.' This clearly defines when to use it versus alternatives, though it doesn't specify when NOT to use it for non-programming queries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the web using Exa AI - performs real-time web searches and can scrape content from specific URLs. Supports configurable result counts and returns the content from the most relevant websites.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Websearch query | |
| numResults | No | Number of search results to return (default: 8) | |
| livecrawl | No | Live crawl mode - 'fallback': use live crawling as backup if cached content unavailable, 'preferred': prioritize live crawling (default: 'fallback') | |
| type | No | Search type - 'auto': balanced search (default), 'fast': quick results, 'deep': comprehensive search | |
| contextMaxCharacters | No | Maximum characters for context string optimized for LLMs (default: 10000) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety and idempotency. The description adds valuable behavioral context beyond annotations: it mentions real-time web searches, scraping from specific URLs, configurable result counts, and returning content from relevant websites. This provides useful operational details without contradicting annotations.
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 appropriately sized at two sentences, front-loading the core purpose. Every sentence adds value: the first defines the tool's function, and the second elaborates on features and output. There's no wasted text, though it could be slightly more structured for optimal clarity.
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's moderate complexity, rich annotations (covering safety and idempotency), and 100% schema coverage, the description is reasonably complete. It explains the tool's function and key features. The lack of an output schema is a minor gap, but the description mentions return content, partially compensating. For a read-only search tool, this provides adequate context.
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 description coverage is 100%, so the schema fully documents all 5 parameters. The description adds minimal parameter semantics beyond the schema, mentioning only 'configurable result counts' (referencing numResults) and 'content from the most relevant websites' (hinting at query relevance). Since the schema does the heavy lifting, the baseline score of 3 is appropriate.
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 clearly states the tool's purpose: 'Search the web using Exa AI - performs real-time web searches and can scrape content from specific URLs.' It specifies the verb (search/scrape) and resource (web/URLs), making the function unambiguous. However, it doesn't explicitly differentiate from its sibling 'get_code_context_exa' beyond mentioning general web search capabilities.
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 implies usage for web searches and content scraping, but provides no explicit guidance on when to use this tool versus its sibling 'get_code_context_exa' or other alternatives. It mentions configurable result counts and relevance, which suggests some context, but lacks clear when/when-not directives or named alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0company_research_exacrawling_exadeep_researcher_checkdeep_researcher_startget_code_context_exalinkedin_search_exaweb_search_exa5 fields changedInput schema / properties / contextMaxCharactersAdded value: +{
+ "description": "Maximum characters for context string optimized for LLMs (default: 10000)",
+ "type": "number"
+}Input schema / properties / livecrawlAdded value: +{
+ "description": "Live crawl mode - 'fallback': use live crawling as backup if cached content unavailable, 'preferred': prioritize live crawling (default: 'fallback')",
+ "enum": [
+ "fallback",
+ "preferred"
+ ],
+ "type": "string"
+}Input schema / properties / numResults / descriptionPrevious value: -"Number of search results to return (default: 5)"New value: +"Number of search results to return (default: 8)"Input schema / properties / query / descriptionPrevious value: -"Search query"New value: +"Websearch query"Input schema / properties / typeAdded value: +{
+ "description": "Search type - 'auto': balanced search (default), 'fast': quick results, 'deep': comprehensive search",
+ "enum": [
+ "auto",
+ "fast",
+ "deep"
+ ],
+ "type": "string"
+}company_research_exacrawling_exadeep_researcher_checkdeep_researcher_startlinkedin_search_exaweb_search_exaScored across 2 tools
The two tools have clearly distinct purposes: get_code_context_exa is specialized for programming-related searches with high-quality code context, while web_search_exa is a general web search tool for broader queries. There is no overlap in functionality, making it easy for an agent to choose the correct tool based on the query content.
Both tools follow a consistent naming pattern: they use snake_case and start with a verb (get, search) followed by a noun (code_context, web). The pattern is uniform across the set, with no deviations in style or structure.
With only 2 tools, the server feels thin for a general-purpose search domain, as it might lack coverage for intermediate or specialized tasks beyond code and web searches. However, the tools are well-defined, so it's borderline but not severely mismatched.
The server covers two key search domains (code and web), but there are notable gaps: it lacks tools for other common search types (e.g., image, news, academic) or advanced operations like filtering or saving results. This could limit agent effectiveness in broader search scenarios.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Provides AI assistants with access to Seltz's powerful Web Search capabilities.
Give AI assistants access to real-time data. Search the web, compare flights, find hotels, and more.
The best web search for your AI Agent
