Deep Research MCP Server

@pinkpixel-dev

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

pinkpixel-dev

关于 Deep Research MCP Server

A Model Context Protocol (MCP) compliant server designed for comprehensive web research. It uses Tavily's Search and Crawl APIs to gather detailed information on a given topic, then structures this data in a format perfect for LLMs to create high-quality markdown documents.

#information-retrieval #knowledge-base #web-crawling #search-api #data-aggregation #research-assistant#documentation-generation#ai-tools #llm #tavily #web-research #deep-research

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": "npx",
      "args": [
        "-y",
        "@pinkpixel/deep-research-mcp"
      ],
      "env": {
        "TAVILY_API_KEY": "YOUR_TAVILY_API_KEY",
        "DOCUMENTATION_PROMPT": "Your custom, detailed instructions for the LLM on how to generate markdown documents from the research data...",
        "RESEARCH_OUTPUT_PATH": "/path/to/your/research/output/folder"
      }
    }
  }
}

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。

点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。

概览

What is Deep Research MCP Server?

Deep Research MCP Server is a Model Context Protocol (MCP) compliant server that performs comprehensive web research using Tavily's Search and Crawl APIs. It gathers extensive information on a topic and outputs structured JSON optimized for Large Language Models (LLMs) to generate detailed markdown documents, and is intended for developers building MCP-based AI agent ecosystems.

How to use Deep Research MCP Server?

Install via npx @pinkpixel/deep-research-mcp or global npm install, then run with a Tavily API key set in the TAVILY_API_KEY environment variable. The server exposes the deep-research-tool for research requests and an optional write-research-file tool for saving results, configured through environment variables or tool arguments.

Key features of Deep Research MCP Server

Multi-step research combining search with deep content crawling
Structured JSON output optimized for LLM consumption
Configurable documentation prompt via environment or tool argument
Configurable output path for saving research documents
Granular control over search and crawl timeouts and limits
Optional secure file writing with path and line restrictions
MCP compliant for integration into AI agent ecosystems

Use cases of Deep Research MCP Server

Generate comprehensive markdown documentation on any topic via an LLM
Automate web research and report generation in MCP-based AI agents
Customize document output with a user-defined documentation prompt
Perform deep content extraction from multiple web sources in a single request
Securely save research findings directly to files through an LLM

常见问题

What are the prerequisites to run the server?

Node.js 18.x or later and npm are required. A Tavily API key must be provided via the `TAVILY_API_KEY` environment variable.

How do I set a custom documentation prompt?

Set the `DOCUMENTATION_PROMPT` environment variable, or pass a `documentation_prompt` argument directly to the `deep-research-tool` call, which takes highest precedence.

Can I control where research files are saved?

Yes, set the `RESEARCH_OUTPUT_PATH` environment variable or pass an `output_path` argument to the tool. By default, files are saved to a timestamped folder in the user's Documents directory.

How do I enable the file-writing capability?

Set `FILE_WRITE_ENABLED=true` in the environment, and optionally restrict allowed directories with `ALLOWED_WRITE_PATHS`. The feature is disabled by default for security.

What security measures are in place for file writing?

Allowed directories are restricted via a comma-separated list, line limits per write operation prevent abuse, and paths are validated and sanitized. Only enable file writing in trusted environments.

数据与分析分类下的更多 MCP 服务器

YouTube MCP Server

HasData

Hosted YouTube MCP server for search, video metadata, channel data and timestamped transcripts. Connect Claude, Cursor or other MCP clients with HasData; no YouTube API key required.

Sugra API MCP

Sugra Systems, Inc.

Official MCP server for the Sugra API, giving AI agents source-attributed access to 1,500+ endpoints across 36 data domains from 160+ primary sources. Covers markets, economics, company fundamentals, government, news, cl

HousingFeed

US rental listings for AI assistants: free live search and rent statistics, plus licensed feeds.

Waqi - AI Privacy Layer

ajprolific

Waqi — hosted MCP server that redacts PII from your business tools before the AI sees them. Audit log included.

CoinLobster

The only MCP server with live whale trades across 15 exchanges plus on-chain DEX flow. Smart Money Radar, real liquidations and outcome-scored signals. No API key required.