DeepSeek 웹 버전 기반의 온라인 검색 MCP 서버입니다. DeepSeek의 검색 강화 대화 기능을 통해 MCP 클라이언트에 실시간 웹 검색 기능을 제공합니다.
실시간 웹 검색을 지원하는 web_search MCP 도구 제공
DeepSeek 기본 모델 및 전문가 모델 지원
사고 과정(thinking) 출력 지원
제로 의존성, 순수 Node.js 구현
stdio 전송, 모든 MCP 클라이언트와 호환
Related MCP server: google-search-mcp
Claude Desktop 설정 파일(claude_desktop_config.json)을 편집하여 env 필드를 통해 자격 증명을 직접 전달합니다. .env 파일은 필요하지 않습니다:
{
"mcpServers": {
"web-search": {
"command": "node",
"args": ["D:/ai-projects/web-search-mcp/src/index.js"],
"env": {
"DEEPSEEK_AUTH_TOKEN": "your_token_here"
}
}
}
}프로젝트의 .claude/settings.json에 다음을 추가합니다:
{
"mcpServers": {
"web-search": {
"command": "node",
"args": ["D:/ai-projects/web-search-mcp/src/index.js"],
"env": {
"DEEPSEEK_AUTH_TOKEN": "your_token_here"
}
}
}
}MCP 설정에 env를 작성하기 불편한 경우 .env 파일을 사용할 수 있습니다:
cp .env.example .env
# 编辑 .env 填入凭据환경 변수 우선순위: 시스템 환경 변수 > MCP
env설정 >.env파일
web_searchDeepSeek 검색 강화 대화를 사용하여 웹 검색을 수행하고, 검색 결과에 기반한 답변을 반환합니다.
매개변수:
매개변수 | 타입 | 필수 | 설명 |
| string | 예 | 검색 쿼리 내용 |
| boolean | 아니오 | DeepSeek 사고/추론 모드 활성화 여부. 활성화 시 모델이 먼저 추론한 후 답변하며, 추론 과정이 응답에 포함됨 (기본값 false) |
| string | 아니오 | 모델 모드: |
변수 | 필수 | 기본값 | 설명 |
| 택일 | - | DeepSeek 로그인 토큰 |
| 택일 | - | DeepSeek 브라우저 쿠키 |
| 아니오 |
| 모델 타입: |
| 아니오 |
| 사고 과정 기본 활성화 여부 |
| 아니오 |
| PoW 솔버 WASM 파일 경로 |
| 아니오 |
| 로그 레벨: |
chat.deepseek.com에 접속하여 로그인합니다.
브라우저 개발자 도구(F12)를 열고 Console(콘솔) 패널로 전환합니다.
다음 명령어를 입력하고 엔터를 누르면 토큰이 복사됩니다:
copy(JSON.parse(localStorage.getItem("userToken")).value)복사된 값을 DEEPSEEK_AUTH_TOKEN 환경 변수에 붙여넣습니다.
주의: 자격 증명은 만료되므로 만료 시 다시 획득해야 합니다. 토큰 만료 시 요청이 Cloudflare 인증 페이지를 반환하는 현상이 발생합니다.
# 运行所有测试
npm test
# 运行单个测试文件
node --test tests/mcp-protocol.test.js
node --test tests/config.test.jssrc/
index.js # 入口，初始化所有组件并启动 MCP 服务器
mcp-server.js # MCP 协议处理（stdio 传输、JSON-RPC 分发）
deepseek-client.js # DeepSeek 网页版 API 客户端（会话管理、PoW、SSE 流式解析）
pow-solver.js # SHA3 PoW WASM 求解器
env.js # .env 文件加载器
config.js # 环境变量配置解析Search the web using DeepSeek's search-enabled chat. Returns a search-grounded response with up-to-date information.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The search query | |
| thinking | No | Enable DeepSeek thinking/reasoning mode. When true, the model will reason through the query before answering, and the reasoning trace is included in the response. (default: false) | |
| model | No | DeepSeek model mode (default: from server config) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description states that the tool returns a 'search-grounded response with up-to-date information', which implies read-only behavior, but it does not explicitly disclose side effects, authentication needs, or limitations. Without annotations, the description carries a heavier burden and falls short of 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 a single sentence that conveys the essential function without unnecessary words. While it is concise, it could be slightly expanded to improve clarity without becoming verbose.
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 that there is no output schema, the description should elaborate on the return format. It mentions 'search-grounded response' but does not specify structure or content. The lack of sibling tools reduces the need for differentiation, but completeness is only moderate.
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 has 100% description coverage for all three parameters, so the baseline is 3. The description adds no extra meaning beyond what the schema already provides for the parameters.
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 uses a specific verb 'Search' and clearly identifies the resource 'the web using DeepSeek's search-enabled chat', leaving no ambiguity about what the tool does.
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 guidance is provided on when to use this tool versus any alternatives, nor are there any conditions or prerequisites mentioned. The description lacks context for appropriate usage.
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.
v0.1.0web_searchScored across 1 tool
Only one tool exists, so there is no possibility of confusion between tools.
The single tool name 'web_search' is clear and follows a common verb_noun pattern, but with only one tool, consistency cannot be fully assessed.
One tool is minimal for a web search server. It covers the core action but may lack supporting tools for refined queries or result handling.
The tool provides basic web search functionality, but there are no tools for advanced filtering, pagination, or retrieving structured results, leaving potential gaps.
Live AI-native web search with citations. One tool for every MCP client. Flat per-request pricing.
Web search, scraping, RAG answers with citations, and translation as MCP tools.
Free web search for AI agents. No API key required. Hosted MCP in active development.
Search the agentic web. 4,100+ sites, 11 tools incl. check_url + verify_mcp for probe-before-use.
