MCP Deep Research
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Deep Research research the latest developments in quantum computing for 2024"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Deep Research
简体中文 | English
Overview
MCP Deep Research is a tool that allows you to search the web for information. It is built with the Model Context Protocol and the Tavily API.
Related MCP server: Tavily MCP Server
Configuration
{
"mcpServers": {
"deep-research": {
"command": "npx",
"args": ["-y", "mcp-deep-research@latest"],
"env": {
"TAVILY_API_KEY": "your_tavily_api_key", // Required
"MAX_SEARCH_KEYWORDS": "5", // Optional, default 5
"MAX_PLANNING_ROUNDS": "5" // Optional, default 5
}
}
}
}The tool can be configured using the following environment variables:
TAVILY_API_KEY: The API key for the Tavily API.MAX_SEARCH_KEYWORDS: The maximum number of search keywords to use.MAX_PLANNING_ROUNDS: The maximum number of planning rounds to use.TAVILY_HTTP_PROXY/TAVILY_HTTPS_PROXY: The proxy address for the Tavily API.
Use with Smithery
Install via Smithery, compatible with Claude Desktop client:
npx -y @smithery/cli install @baranwang/mcp-deep-research --client claudeCompatibility Notice
This MCP server is optimized for prompt-based MCP clients. For MCP clients implemented using function calling mechanisms, the performance and results may not be optimal.
Verified prompt-based MCP clients:
Verified function calling-based MCP clients:
Available Tools
1 tooldeep-researchC
Deep web information search tool that can conduct multi-round in-depth research based on keywords and topics
Inputs: question (required), reference, keywords, topic, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possible confusion between overlapping functions. The single tool has a clear, distinct purpose.
The single tool name 'deep-research' is lowercase hyphens, consistent and descriptive of the action. There are no other names to conflict.
One tool is quite thin for a deep research capability, though the tool explicitly says it conducts multi-round research internally, making a single entry point feasible. It borders between too few and acceptable for a narrow scope.
The tool covers the full research workflow in one call, including multi-round searching. Minor gaps exist around controlling research depth, output formats, or retrieving past research, but the core purpose is served.
Maintenance
Related MCP Connectors
Real-time web search, reasoning, and research through Perplexity's API
Real-time web and scholarly search with cited answers and multi-step deep research.
Web search, fetch, extract, and research for AI agents. Markdown output + AI-synthesized answers.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceProvides AI-powered web search capabilities using Tavily's search API, enabling LLMs to perform sophisticated web searches, get direct answers to questions, and search recent news articles.72MIT
- AlicenseNot gradedqualityFmaintenanceEnables AI assistants to perform up-to-date web searches through the Tavily API, providing comprehensive search results with AI-generated summaries.7MIT
- FlicenseCqualityDmaintenanceEnables web search capabilities through the Tavily API, allowing users to perform web searches and retrieve information from the internet through natural language queries.3-
- FlicenseNot gradedqualityDmaintenanceProvides web search capabilities using the Tavily API, enabling AI models to search the internet and retrieve up-to-date information.-