빠르고 무료 실시간 웹 검색을 지원하고 뉴스, 금융 시장, 스포츠, 엔터테인먼트, 날씨 등 신뢰할 수 있는 미디어 브랜드의 프리미엄 데이터에 액세스하세요. Dappier로 강력한 AI 에이전트를 구축하세요.
marketplace.dappier.com 에서 다양한 데이터 모델을 살펴보세요.
이미지를 클릭하면 Claude Desktop으로 Dappier MCP를 설정하는 방법에 대한 전체 비디오 가이드를 볼 수 있습니다 .
Related MCP server: Deep Research MCP Server
Dappier API 키를 받으세요. Dappier 에 접속하여 가입하고 API 키를 생성하세요.
Smithery를 통해 Claude Desktop용 dappier-mcp를 자동으로 설치하려면:
지엑스피1
먼저 uv 설치하세요.
맥OS/리눅스 :
curl -LsSf https://astral.sh/uv/install.sh | sh윈도우 :
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"다음 내용으로 Claude 구성 파일( claude_desktop_config.json )을 업데이트하세요.
{
"mcpServers": {
"dappier": {
"command": "uvx",
"args": ["dappier-mcp"],
"env": {
"DAPPIER_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}힌트 :
command필드에uvx실행 파일의 전체 경로를 입력해야 할 수 있습니다. macOS/Linux에서는which uvx, Windows에서는where uvx실행하여 경로를 확인할 수 있습니다.
구성 파일 위치:
macOS : ~/Library/Application Support/Claude/claude_desktop_config.json
윈도우 : %APPDATA%\Claude\claude_desktop_config.json
애플리케이션을 통해 접근:
맥OS :
Claude Desktop 애플리케이션을 엽니다.
메뉴 표시줄에서 Claude > Settings 클릭합니다.
Developer 탭으로 이동합니다.
기본 텍스트 편집기에서 구성 파일을 열려면 Edit Config 클릭하세요.
윈도우 :
Claude Desktop 애플리케이션을 엽니다.
기어 아이콘을 클릭하여 Settings 에 접근하세요.
Developer 탭으로 이동합니다.
기본 텍스트 편집기에서 구성 파일을 열려면 Edit Config 클릭하세요.
참고 :
Developer탭이 보이지 않으면 최신 버전의 Claude Desktop을 사용하고 있는지 확인하세요.
다음 내용으로 커서 구성 파일( mcp.json )을 업데이트하세요.
{
"mcpServers": {
"dappier": {
"command": "uvx",
"args": ["dappier-mcp"],
"env": {
"DAPPIER_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}힌트 :
command필드에uvx실행 파일의 전체 경로를 입력해야 할 수 있습니다. macOS/Linux에서는which uvx, Windows에서는where uvx실행하여 경로를 확인할 수 있습니다.
구성 파일 위치:
글로벌 구성 :
macOS : ~/.cursor/mcp.json
윈도우 : %USERPROFILE%\.cursor\mcp.json
프로젝트별 구성 :
프로젝트 폴더 내 .cursor 디렉토리에 mcp.json 파일을 넣으세요: <project-root>/.cursor/mcp.json
애플리케이션을 통해 접근:
커서 애플리케이션을 엽니다.
Settings > MCP 로 이동합니다.
Add New Global MCP Server 클릭합니다.
이 애플리케이션은 편집을 위해 기본 텍스트 편집기에서 mcp.json 파일을 엽니다.
참고 : Windows에서 프로젝트 수준 구성이 인식되지 않으면 커서 설정 인터페이스를 통해 MCP 서버를 추가하는 것을 고려하세요.
다음 내용으로 Windsurf 구성 파일( mcp_config.json )을 업데이트하세요.
{
"mcpServers": {
"dappier": {
"command": "uvx",
"args": ["dappier-mcp"],
"env": {
"DAPPIER_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}힌트 :
command필드에uvx실행 파일의 전체 경로를 입력해야 할 수 있습니다. macOS/Linux에서는which uvx, Windows에서는where uvx실행하여 경로를 확인할 수 있습니다.
구성 파일 위치:
macOS : ~/.codeium/windsurf/mcp_config.json
윈도우 : %USERPROFILE%\.codeium\windsurf\mcp_config.json
애플리케이션을 통해 접근:
Windsurf 앱을 엽니다.
Settings > Cascade 으로 이동합니다.
Model Context Protocol (MCP) Servers 섹션까지 아래로 스크롤합니다.
기본 텍스트 편집기에서 mcp_config.json 파일을 열려면 View raw config 클릭합니다.
참고 : 구성 파일을 편집한 후 MCP 서버 섹션에서
Refresh버튼을 클릭하여 변경 사항을 적용합니다.
Dappier MCP 원격 서버는 별도의 교육이나 미세 조정 없이 바로 사용할 수 있는 강력한 실시간 기능을 제공합니다. 이를 사용하여 최신 웹 데이터, 금융 시장 또는 AI 기반 콘텐츠를 기반으로 하는 실시간 인터랙티브 도구를 구축하세요.
모델 ID: am_01j06ytn18ejftedz6dyhz2b15
Dappier의 AI 기반 인덱스를 사용하여 실시간 웹을 검색하세요. 다음 항목에 실시간으로 접속하세요.
전 세계의 최신 뉴스
날씨 예보 및 지역 업데이트
여행 알림 및 항공편 정보
인기 주제 및 바이럴 콘텐츠
온라인 딜 및 쇼핑 하이라이트
뉴스 에이전트, 여행 기획자, 알림 봇 등의 사용 사례에 이상적입니다.
모델 ID: am_01j749h8pbf7ns8r1bq9s2evrh
이 모델은 시장 데이터, 금융 뉴스, 거래 인사이트에 대한 즉각적인 접근을 제공합니다. 포트폴리오 대시보드, 트레이딩 코파일럿, 투자 도구에 적합합니다.
다음이 제공됩니다.
실시간 주가
재정 뉴스 및 회사 업데이트
거래 신호 및 추세
시장 움직임 요약
Polygon.io의 라이브 데이터를 활용한 AI 큐레이션 분석
콘텐츠 검색, 요약 및 피드 생성에 맞춰 제작된 다양한 도메인별 AI 모델 중에서 선택하세요.
모델 ID: dm_01j0pb465keqmatq9k83dthx34
실시간 스포츠 헤드라인, 경기 요약, 전문가 분석으로 최신 소식을 받아보세요.
모델 ID: dm_01j0q82s4bfjmsqkhs3ywm3x6y
웰빙, 엔터테인먼트, 일상의 영감 등 엄선된 라이프스타일 콘텐츠를 살펴보세요.
모델 ID: dm_01j1sz8t3qe6v9g8ad102kvmqn
귀하의 지능형 반려견 케어 도우미 - 훈련 팁, 건강 조언, 행동 통찰력을 확인하세요.
모델 ID: dm_01j1sza0h7ekhaecys2p3y0vmj
고양이에 관한 모든 것, 즉 영양 공급부터 놀이 시간, 손질 루틴까지 전 과정을 담당하는 전문 AI입니다.
모델 ID: dm_01j5xy9w5sf49bm6b1prm80m27
지속 가능한 라이프스타일 아이디어, 윤리적 선택, 친환경 혁신을 발견해 보세요.
모델 ID: dm_01jagy9nqaeer9hxx8z1sk1jx6
하이퍼로컬 뉴스, 정치, 문화, 건강, 다문화 최신 소식을 받아보세요.
각 권장 사항에는 다음이 포함됩니다.
명확한 제목과 간결한 요약
원래 출판 날짜
신뢰할 수 있는 소스 및 도메인
이미지 미리보기(가능한 경우)
우선순위 지정을 위한 관련성 점수
고급 옵션을 사용하면 다음을 수행할 수 있습니다.
검색 알고리즘을 조정합니다( semantic , most_recent , trending 등)
특정 도메인에 초점을 맞춘 결과( ref )
원하는 결과 수를 조정하세요( similarity_top_k , num_articles_ref )
MCP 검사기를 실행하여 서버를 디버깅합니다.
npx @modelcontextprotocol/inspector uvx dappier-mcpDappier MCP 서버 확장 및 개선을 위한 여러분의 참여를 환영합니다. 새로운 검색 기능 추가, 기존 기능 개선, 또는 문서 개선 등 어떤 목적이든 여러분의 의견은 소중합니다.
다른 MCP 서버 및 구현 패턴의 예는 https://github.com/modelcontextprotocol/servers를 참조하세요.
풀 리퀘스트를 환영합니다! 새로운 아이디어, 버그 수정, 개선 사항 등을 자유롭게 공유해 주세요.
Fetch AI-powered recommendations from Dappier by processing the provided query with a selected data model that tailors results to specific interests.
- **Sports News (dm_01j0pb465keqmatq9k83dthx34):**
Get real-time news, updates, and personalized content from top sports sources.
- **Lifestyle News (dm_01j0q82s4bfjmsqkhs3ywm3x6y):**
Access current lifestyle updates, analysis, and insights from leading lifestyle publications.
- **iHeartDogs AI (dm_01j1sz8t3qe6v9g8ad102kvmqn):**
Tap into a dog care expert with access to thousands of articles covering pet health, behavior, grooming, and ownership.
- **iHeartCats AI (dm_01j1sza0h7ekhaecys2p3y0vmj):**
Utilize a cat care specialist that provides comprehensive content on cat health, behavior, and lifestyle.
- **GreenMonster (dm_01j5xy9w5sf49bm6b1prm80m27):**
Receive guidance for making conscious and compassionate choices benefiting people, animals, and the planet.
- **WISH-TV AI (dm_01jagy9nqaeer9hxx8z1sk1jx6):**
Get recommendations covering sports, breaking news, politics, multicultural updates, and more.
Based on the chosen `data_model_id`, the tool processes the input query and returns a formatted summary including article titles, summaries, images, source URLs, publication dates, and relevance scores.
| Name | Required | Description | Default |
|---|---|---|---|
| ref | No | The site domain where recommendations should be prioritized. | |
| query | Yes | The input string for AI-powered content recommendations. | |
| data_model_id | Yes | The data model ID to use for recommendations. Available Data Models: - dm_01j0pb465keqmatq9k83dthx34: (Sports News) Real-time news, updates, and personalized content from top sports sources like Sportsnaut, Forever Blueshirts, Minnesota Sports Fan, LAFB Network, Bounding Into Sports and Ringside Intel. - dm_01j0q82s4bfjmsqkhs3ywm3x6y: (Lifestyle News) Real-time updates, analysis, and personalized content from top sources like The Mix, Snipdaily, Nerdable and Familyproof. - dm_01j1sz8t3qe6v9g8ad102kvmqn: (iHeartDogs AI) A dog care expert with access to thousands of articles on health, behavior, lifestyle, grooming, ownership, and more from the industry-leading pet community iHeartDogs.com. - dm_01j1sza0h7ekhaecys2p3y0vmj: (iHeartCats AI) A cat care expert with access to thousands of articles on health, behavior, lifestyle, grooming, ownership, and more from the industry-leading pet community iHeartCats.com. - dm_01j5xy9w5sf49bm6b1prm80m27: (GreenMonster) A helpful guide to making conscious and compassionate choices that benefit people, animals, and the planet. - dm_01jagy9nqaeer9hxx8z1sk1jx6: (WISH-TV AI) Covers sports, politics, breaking news, multicultural news, Hispanic language content, entertainment, health, and education. | |
| num_articles_ref | No | Minimum number of articles to return from the reference domain. | |
| search_algorithm | No | The search algorithm to use for retrieving articles. | most_recent |
| similarity_top_k | No | Number of top similar articles to retrieve based on semantic similarity. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It describes the output as a 'formatted summary including article titles, summaries, images, source URLs, publication dates, and relevance scores,' which is helpful. However, it does not mention authorization requirements, rate limits, or side effects, which would be expected for a tool with no 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 starts with a clear purpose and organizes data models with bullet points, but it is somewhat verbose by repeating model information that is also in the schema. It is front-loaded but could be more concise, as every sentence earns its place but some repetition exists.
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 six parameters, no output schema, and 100% schema coverage, the description is nearly complete. It explains the output format and each data model's domain, covering the core functionality. It could be more complete by briefly explaining how ref, num_articles_ref, search_algorithm, and similarity_top_k affect results, but the schema handles those sufficiently.
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 baseline is 3. The description adds value by naming and explaining data model IDs (e.g., 'Sports News: Real-time news...'), but these details are already present in the schema's description for data_model_id. Other parameters like ref, query, and search_algorithm are not elaborated beyond the schema, so the description provides minimal additional meaning.
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 'Fetch AI-powered recommendations from Dappier by processing the provided query with a selected data model,' which identifies the verb (fetch recommendations) and resource (Dappier data models). It distinguishes the tool from the sibling dappier_real_time_search by emphasizing recommendations with tailored content, though it doesn't explicitly contrast them.
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 by listing data models and their domains (e.g., Sports News, Lifestyle News), but it does not explicitly state when to use this tool over the sibling or provide conditions for use. It lacks exclusions or alternative suggestions, leaving the agent to infer context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve real-time search data from Dappier by processing an AI model that supports two key capabilities:
- Real-Time Web Search:
Access the latest news, weather, travel information, deals, and more using model `am_01j06ytn18ejftedz6dyhz2b15`.
- Stock Market Data:
Retrieve real-time financial news, stock prices, and trade updates using model `am_01j749h8pbf7ns8r1bq9s2evrh`.
Based on the provided `ai_model_id`, the tool selects the appropriate model and returns search results.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The search query to retrieve real-time information. | |
| ai_model_id | Yes | The AI model ID to use for the query. Available AI Models: - am_01j06ytn18ejftedz6dyhz2b15: (Real Time Data) Access real-time Google web search results, including the latest news, weather, travel, deals, and more. - am_01j749h8pbf7ns8r1bq9s2evrh: (Stock Market Data) Access real-time financial news, stock prices, and trades from Polygon.io, with AI-powered insights and up-to-the-minute updates. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behaviors. It mentions that an AI model is selected based on ai_model_id and returns results, but it does not address side effects, permissions, rate limits, error handling, or return structure. This is insufficient for full transparency.
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 concise, well-structured into two paragraphs, and front-loads the purpose. Every sentence adds value with no redundancy.
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 no output schema, no annotations, and two distinct models, the description lacks details on return format, error scenarios, and guidance on model selection. It is incomplete for effective agent use.
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% with detailed descriptions for both parameters. The description adds no meaningful new information beyond what is already in the schema, so it meets the baseline without enhancement.
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 'Retrieve real-time search data from Dappier' and distinguishes between two specific capabilities (web search and stock market data) using model IDs. The tool name and description differentiate it from the sibling tool 'dappier_ai_recommendations' by focusing on real-time data retrieval.
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 lists two use cases but does not explicitly guide when to use this tool versus the sibling tool. It implies usage context through capabilities but lacks direct instructions or exclusions.
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.
v1.0.0dappier_ai_recommendationsdappier_real_time_searchScored across 2 tools
The two tools have clearly distinct purposes: one fetches AI recommendations with various data models, the other performs real-time search. No overlap in functionality.
Both tools share the 'dappier_' prefix and use descriptive noun phrases ('ai_recommendations', 'real_time_search'), though the first uses underscores between words and the second uses a more compound adjective form, leading to minor inconsistency.
With only 2 tools, the server is very focused. For a purpose-built API covering recommendations and search, this number is reasonable though minimal. Slightly under the typical 3-15 range but not drastically.
The server covers its stated domains (recommendations and real-time search) adequately, but lacks tools for managing data models or retrieving raw content. It's sufficient for basic use but leaves out potential CRUD operations.
Real-time data API for AI Agents: stocks, weather, forex, logistics, search, scrape, news, IP.
Structured, cited, real-world data from 300+ sources and the open web for your AI agents.
Give your agent web search and authoritative datasets: S&P Global, FRED, OECD, SimilarWeb & more.
Web data for agents: YouTube transcripts, screenshots, Google News, WHOIS, jobs, tech stack, more.
