deep-research
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
- 4.7k estrellas
- 1.1k forks
- 42 issues abiertos
- Lenguaje: JavaScript
- Licencia: MIT
- actualizado
Instalación
git clone https://github.com/u14app/deep-research{
"mcpServers": {
"deep-research": {
"command": "node",
"args": ["/path/to/deep-research/dist/index.js"]
}
}
}{
"mcpServers": {
"deep-research": {
"command": "node",
"args": ["/path/to/deep-research/dist/index.js"]
}
}
}- Run the command above in your terminal (Claude Code), or paste the JSON config into claude_desktop_config.json (Claude Desktop).
- Replace any <placeholder> values with your API keys or paths.
- Restart Claude. The MCP server and its tools appear automatically.
Clone https://github.com/u14app/deep-research and follow its README for install instructions.
Nota editorial
Deep Research is a Next.js 15 application and MCP server that generates multi-section research reports by coordinating two distinct model roles: a "Thinking" model for planning and a "Task" model for execution, completing a full report in roughly two minutes. It connects to Claude and other LLMs through direct API integration, supporting Anthropic alongside OpenAI, Gemini, DeepSeek, Grok, Mistral, Azure OpenAI, OpenRouter, and Ollama. Web search is handled through configurable backends including Tavily, Firecrawl, Exa, Brave, and Searxng. The MCP server mode allows Claude Desktop and other MCP-compatible clients to call Deep Research as an external tool. Users can upload text, Office, and PDF files to build a local knowledge base, generate knowledge graphs from completed reports, and edit outputs in either WYSIWYM or Markdown mode. All data is stored locally in the browser rather than on external servers, which suits researchers and developers who want a self-hosted, privacy-preserving alternative to managed research services.
Resumen de MCP Servers
Lo que la gente pregunta sobre deep-research
¿Qué es u14app/deep-research?
u14app/deep-research es mcp servers para el ecosistema de Claude AI. Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server. Tiene 4.7k estrellas en GitHub y su última actualización registrada es del 2026-06-18.
¿Cómo se instala deep-research?
Puedes instalar deep-research clonando el repositorio (https://github.com/u14app/deep-research) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar u14app/deep-research?
Nuestro agente de seguridad ha analizado u14app/deep-research y le ha asignado un Trust Score de 92/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene u14app/deep-research?
u14app/deep-research es mantenido por u14app. La última actividad registrada en GitHub es del 2026-06-18, con 42 issues abiertos.
¿Hay alternativas a deep-research?
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.