Servidor MCP de búsqueda en línea basado en la versión web de DeepSeek. Proporciona capacidades de búsqueda web en tiempo real a clientes MCP a través de la función de diálogo mejorado con búsqueda de DeepSeek.
Proporciona la herramienta MCP web_search, que admite búsqueda web en tiempo real
Admite modelos predeterminados y modelos expertos de DeepSeek
Admite la salida del proceso de pensamiento (thinking)
Cero dependencias, implementación pura en Node.js
Transporte stdio, compatible con todos los clientes MCP
Related MCP server: google-search-mcp
Edite el archivo de configuración de Claude Desktop (claude_desktop_config.json) y pase las credenciales directamente a través del campo env, sin necesidad de un archivo .env:
{
"mcpServers": {
"web-search": {
"command": "node",
"args": ["D:/ai-projects/web-search-mcp/src/index.js"],
"env": {
"DEEPSEEK_AUTH_TOKEN": "your_token_here"
}
}
}
}Agregue lo siguiente en el archivo .claude/settings.json del proyecto:
{
"mcpServers": {
"web-search": {
"command": "node",
"args": ["D:/ai-projects/web-search-mcp/src/index.js"],
"env": {
"DEEPSEEK_AUTH_TOKEN": "your_token_here"
}
}
}
}Si no es conveniente escribir env en la configuración de MCP, también puede usar un archivo .env:
cp .env.example .env
# 编辑 .env 填入凭据Prioridad de las variables de entorno: Variables de entorno del sistema > Configuración
envde MCP > Archivo.env
web_searchUtiliza el diálogo mejorado con búsqueda de DeepSeek para realizar búsquedas web y devuelve respuestas basadas en los resultados de la búsqueda.
Parámetros:
Parámetro | Tipo | Obligatorio | Descripción |
| string | Sí | Contenido de la consulta de búsqueda |
| boolean | No | Si se debe activar el modo de pensamiento/razonamiento de DeepSeek. Si se activa, el modelo razonará antes de responder y el proceso de razonamiento se incluirá en la respuesta (predeterminado: false) |
| string | No | Modo de modelo: |
Variable | Obligatorio | Valor predeterminado | Descripción |
| Uno de dos | - | Token de inicio de sesión de DeepSeek |
| Uno de dos | - | Cookie del navegador de DeepSeek |
| No |
| Tipo de modelo: |
| No |
| Si se debe habilitar el proceso de pensamiento por defecto |
| No |
| Ruta del archivo WASM del solucionador PoW |
| No |
| Nivel de registro: |
Abra chat.deepseek.com e inicie sesión
Abra las herramientas de desarrollo del navegador (F12) → cambie al panel Console (Consola)
Ingrese el siguiente comando y presione Enter para copiar el token:
copy(JSON.parse(localStorage.getItem("userToken")).value)Péguelo en la variable de entorno DEEPSEEK_AUTH_TOKEN
Nota: Las credenciales caducan y deben obtenerse de nuevo cuando expiren. Una señal típica de que el token ha caducado es que la solicitud devuelva una página de verificación de Cloudflare.
# 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.
