deep-research
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
Deep Research is an MCP server that conducts comprehensive research on any topic using various large language models and web search engines. It generates detailed research reports by orchestrating specialized "thinking" and "task" models, automatically gathering information from the internet or local knowledge bases, and synthesizing findings into structured Markdown documents. The server supports both StreamableHTTP and SSE transport protocols, enabling integration with MCP-compatible AI clients. Developers can configure multiple AI providers (Gemini, OpenAI, Anthropic, DeepSeek, and others) alongside search engines like Tavily, SearXNG, and Firecrawl.
Key Features
Use Cases
- 01Augmenting AI assistants with comprehensive research capabilities on complex topics
- 02Automating literature reviews by gathering and synthesizing information from web sources
- 03Generating briefing documents that combine internet research with private document collections
- 04Conducting competitive analysis research through orchestrated AI model workflows
- 05Creating knowledge graphs and structured reports from unstructured research data
- 06Building research-enhanced chatbots and AI agents using the MCP protocol
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
deep-research — FAQ
What is the deep-research MCP server?+
It's an MCP server that enables AI assistants to conduct in-depth research by orchestrating multiple AI models and search engines, then synthesizing findings into comprehensive reports. All research data is processed through the Model Context Protocol for seamless integration with compatible clients.
How do I install and connect the deep-research MCP server?+
Deploy the application to Vercel, Cloudflare, or run it via Docker, then add the server configuration to your MCP client's settings file pointing to your deployment URL with StreamableHTTP or SSE transport. Set required environment variables for your chosen AI provider and search engine.
Which MCP clients work with deep-research?+
Any MCP-compatible client that supports StreamableHTTP or SSE transport can connect to deep-research. You must configure a timeout of at least 600 seconds due to the lengthy research process.
Do I need API keys to use this MCP server?+
Yes, you need API keys for at least one AI provider (such as Gemini, OpenAI, or Anthropic) and optionally for search engines like Tavily or Firecrawl. Environment variables like MCP_AI_PROVIDER, MCP_THINKING_MODEL, and MCP_TASK_MODEL must be configured.
Is the deep-research MCP server free?+
The software is open-source under the MIT License and free to use. However, you'll incur costs from the AI provider and search engine APIs you configure it to use.
What are the timeout requirements for this MCP server?+
Deep research tasks typically take around 2 minutes or longer to complete, so you must configure your MCP client with a timeout of at least 600 seconds to prevent premature connection termination during active research.
How do I install deep-research?+
Open the source repository on GitHub and follow its README. deep-research is a mcp server — MCP Agents Market links you directly to the official repo.
Is deep-research free?+
deep-research is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.