Deep Research MCP Server
by pinkpixel-dev · ai-ml · mcp-server, lobehub, validated, science-education
A Model Context Protocol (MCP) compliant server for comprehensive web research using Tavily's Search and Crawl APIs. It aggregates data into structured JSON optimized for LLM documentation generation. Requires a Tavily API key set via the TAVILY_API_KEY environment variable. Optional environment variables allow configuring documentation prompts, output paths, timeouts, crawl limits, and secure file writing settings.
Source: https://github.com/MCP-Mirror/pinkpixel-dev_deep-research-mcp
Install
git clone https://github.com/MCP-Mirror/pinkpixel-dev_deep-research-mcpUse this forAI-extracted
- →Conduct comprehensive research on technical topics and compile findings into structured reports
- →Gather competitive intelligence by analyzing multiple sources and synthesizing insights
- →Support literature reviews and evidence gathering for decision-making in software projects
Works with
Tags: mcp-server, lobehub, validated, science-education
⭐ 117 GitHub stars · Source: lobehub
About ai-ml MCP servers and Claude skills
ai-ml MCP servers extend what AI agents can do inside Claude Code, Cursor, Copilot, Codex, and Windsurf. The Skiln directory indexes 16,000+ such integrations across 22 categories.
Deep Research MCP Server is one of hundreds of ai-ml entries indexed on Skiln. Browse the full ai-ml category or the complete directory of Claude skills, MCP servers, agents, commands, and hooks.
Related ai-ml MCPs and skills
- Vibe Check MCP by PV-Bhat
Metacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety. No external data files required.
- Figma Dev Mode MCP 服务器指南 by figma
Dev Mode MCP 服务器将 Figma 直接集成到您的工作流程中，提供重要的设计信息和上下文，帮助 AI 代理从 Figma 设计文件生成代码。该服务器在本地运行于 Figma 桌面应用程序内，监听 http://127.0.0.1:3845/mcp，无需外部数据文件。
- Hermes MCP Bridge by jigsgfx
Read-only MCP bridge exposing Hermes gateway monitoring tools (status, mission control, channels, approvals) to ChatGPT via HTTP/SSE.
- tomsk-transport by atBuba
MCP server providing real-time public transport data for Tomsk, including routes, schedules, stops with lazy OSM enrichment, nearby stop search, and a routing prompt for LLMs.
- edgemem by AnuwatThisuka
Filesystem-native agent memory for Claude Code, enabling persistent team context across sessions through cloud-synced memory files and MCP tools.
- DOC-Intelligence-MCP-SERVER by SARAN-KUMAR-S
Enables LLMs to dynamically search, scrape, and query official documentation of libraries like uv, OpenAI, LangChain, and LlamaIndex via Google Serper and Groq.
- @context-anchor/mcp-server by DevDario
Git-native MCP server for managing AI context across sessions. Enables LLMs to access project and feature context via markdown files, preserving decisions and constraints.
- opencode-mcp-tool by withakay
This is a Model Context Protocol (MCP) server that allows AI assistants to interact with the OpenCode CLI. It enables AI assistants to leverage multiple AI models through a unified interface, with features like plan mode for structured thinking and extensive model selection.
Frequently asked questions
How do I install Deep Research MCP Server?
Add the install command above to your Claude Code, Cursor, or Windsurf MCP configuration. Most servers register via npx, a local command, or a Docker image. Refer to the source repository for environment variables and credential requirements.
Which clients support Deep Research MCP Server?
Any MCP-compatible client works: Claude Desktop, Claude Code CLI, Cursor, Windsurf, Zed, and VS Code with the official MCP extension. OpenAI Codex and GitHub Copilot increasingly support MCP via adapter bridges.
Is Deep Research MCP Server free?
The server itself is typically open source. Any upstream service (API keys, paid tiers, hosted infrastructure) may have its own pricing. Check the source repository for details.