广告合作
MCP.so
登录

Deep Research MCP Server

@u14app

代码仓库主页

基本信息

分类

数据与分析

许可证

MIT

传输方式

stdio

作者

u14app

关于 Deep Research MCP Server

Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.

#gemini#openai#grok#anthropic#ollama#deepseek#mcp-server#deep-research#deepresearch

Deep Research MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "deep-research": {
      "command": "docker",
      "args": [
        "pull",
        "xiangfa/deep-research:latest"
      ]
    }
  }
}

Deep Research MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Deep Research?

Deep Research is an open-source AI-powered tool that generates in-depth research reports in about two minutes. It supports multiple large language models and search engines, processes and stores all data locally in the browser to protect user privacy, and can be deployed on Vercel, Cloudflare, Docker, or as a static site.

How to use Deep Research?

Use the free Gemini model by obtaining a Gemini API key, then deploy the project with a one-click button to Vercel or Cloudflare, and start using. For other LLMs, set the LLM API key and optional API base URL after deployment. For local development, clone the repository, install dependencies with pnpm, set environment variables via env.tpl, and run pnpm dev.

Key features of Deep Research

  • Rapid deep research reports in about two minutes.
  • Privacy-focused: all data stored locally in the browser.
  • Supports multiple LLMs including Gemini, OpenAI, Anthropic, Deepseek, etc.
  • Supports multiple web search engines like Tavily, Firecrawl, Searxng, etc.
  • Offers both local API and server-side API (SSE and MCP).
  • Includes local knowledge base, artifact editing, and knowledge graph features.

Use cases of Deep Research

  • Quickly generate comprehensive research reports on any topic.
  • Perform iterative research by refining or adjusting at any stage.
  • Use as a SaaS service via its SSE API or integrate with other AI tools via the MCP server.
  • Build a local knowledge base from uploaded text, Office, and PDF files.

常见问题

1

How does Deep Research protect my privacy?

All data is processed and stored locally in your browser. When using the local API mode, no API keys or server-side configurations are needed.

2

Which AI models and search engines does Deep Research support?

It supports Gemini, OpenAI, Anthropic, Deepseek, Atlas Cloud, Grok, Mistral, Azure OpenAI, OpenAI-compatible LLMs, OpenRouter, Ollama, etc. For search, it supports Searxng, Tavily, Firecrawl, fastCRW, Exa, Bocha, Brave, and others.

3

Can I deploy Deep Research myself?

Yes, you can deploy it on Vercel, Cloudflare Pages, using Docker, or as a static export. Detailed guides are provided for each method.

4

Does Deep Research support APIs for integration with other tools?

Yes, it provides a Server-Sent Events (SSE) API and a Model Context Protocol (MCP) server. You can use the SSE API to start research tasks and receive real-time results.

5

Is the project open-source?

Yes, Deep Research is MIT licensed and freely available for personal and commercial use.

评论

数据与分析 分类下的更多 MCP 服务器

hedwigai

hedwigai

Research workbooks your agent keeps current: spreadsheets and memos where every figure cites its primary source (SEC filings, customs records, trial registries), plus data programs such as website traffic for 1,000 domai

Statable

Key Arg B.V.

Privacy-first, cookieless web analytics hosted in the EU. Query visitors, pages, traffic sources, countries, goals, funnels and live traffic for your sites, and create sites, goals and funnels — 25 tools over OAuth.

Companero – Romanian Company Data

Companero

Remote MCP server for Romanian company data: search 2.7M Romanian companies by CUI, county, CAEN industry, revenue and founding date; get company profiles, balance sheets, ANAF tax debts, legal representatives and due di

Instagram MCP Server

HasData

Read public Instagram profiles and post feeds by handle in Claude, Cursor, and other MCP clients. Get follower counts, captions, hashtags, mentions, and engagement counts as structured JSON.

23

ScrapeCheck

FieldmodeLLC

Verify scraped data against the live source page. Signed verdicts, $0.01 via x402.

广告合作