AIbase
EN
Explore
Deep Rsrch Gemini
D

Deep Rsrch Gemini

A multi-agent deep research system based on MCP, integrating LinkUp search, CrewAI coordination, and the Gemini large model, providing an interactive interface through Streamlit.
Research and dataDeveloper tools#Intelligent research#Multi-agent#Deep search#AI coordination.Python
2.5 points
0

What is the MCP server?

The MCP server is a dedicated server designed based on the Model Context Protocol, used to run complex multi-agent systems. In this case, it is used to perform in-depth web searches and information analysis tasks.

How to use the MCP server?

Define server parameters by configuring a JSON file and start the service in the specified directory. This server can be integrated into other systems to provide in-depth research capabilities.

Applicable scenarios

Suitable for scenarios that require large-scale web data collection, information organization, and analysis, such as market research, academic research, and news tracking.

Main Features

Multi-agent collaborationSupports multiple intelligent agents working together to complete complex task division and execution.
Deep web searchUtilizes the LinkUp API for in-depth web searches to obtain more comprehensive information resources.
Natural language processingBased on the Gemini model, it can understand and generate natural language content, enhancing the interaction experience.
Visual interfaceBuilds an intuitive user interface through Streamlit, facilitating non-technical personnel to operate.

Advantages and Limitations

Advantages
Efficiently handle complex information retrieval tasks
Support multiple agent collaboration modes to improve work efficiency
Easy to integrate into existing systems
Provide an intuitive user interface to lower the usage threshold
Limitations
Dependent on the availability and stability of external APIs (such as LinkUp)
Require a certain technical foundation for configuration and deployment
Have certain requirements for computing resources

How to Use

Install dependencies
Ensure that all dependency packages are installed in the project root directory. You can complete the installation through the `uv sync` command.
Configure environment variables
Set the API keys for LinkUp and Gemini to ensure that the server can access external services normally.
Start the server
Run the server script in the project directory to start providing MCP services.
Run the application
Use Streamlit to start the front-end application and access and operate the MCP server through a browser.

Usage Examples

Market research analysisUse the MCP server to automatically collect industry reports, market trend analyses, etc., to help users quickly understand market dynamics.
Academic research assistanceRetrieve relevant literature, research reports, and data analyses through the MCP server to support academic research.

Frequently Asked Questions

What hardware configurations are required for the MCP server?
How to obtain the API keys for LinkUp and Gemini?
Does the MCP server support remote access?
If an error occurs, how to troubleshoot the problem?

Related Resources

LinkUp Official Website
Obtain the LinkUp API key and learn more about its features
CrewAI Official Documentation
Understand the CrewAI framework and the design principles of agents
Gemini API Guide
Get detailed instructions and usage methods for the Gemini API
Streamlit Official Documentation
Learn how to use Streamlit to build interactive web applications
Installation
Copy the following command to your Client for configuration
{
  "mcpServers": {
    "crew_research": {
      "command": "uv",
      "args": [
        "--directory",
        "./Multi-Agent-deep-researcher-mcp-windows-linux",
        "run",
        "server.py"
      ],
      "env": {
        "LINKUP_API_KEY": "your_linkup_api_key_here",
        "GEMINI_API_KEY": "your_gEMINI_API_KEY"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.
Z
Zen MCP Server
Zen MCP is a multi-model AI collaborative development server that provides enhanced workflow tools and cross-model context management for AI coding assistants such as Claude and Gemini CLI. It supports seamless collaboration of multiple AI models to complete development tasks such as code review, debugging, and refactoring, and can maintain the continuation of conversation context between different workflows.
Python
17
5 points
C
Container Use
Container Use is an open-source tool that provides a containerized isolated environment for coding agents, supporting parallel development of multiple agents without interference.
Go
12
5 points
S
Search1api
The Search1API MCP Server is a server based on the Model Context Protocol (MCP), providing search and crawling functions, and supporting multiple search services and tools.
TypeScript
374
4 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
889
4.3 points
M
MCP Server Airbnb
Certified
MCP service for Airbnb listing search and details query
TypeScript
274
4 points
M
MCP Alchemy
Certified
MCP Alchemy is a tool that connects Claude Desktop to multiple databases, supporting SQL queries, database structure analysis, and data report generation.
Python
359
4.2 points
P
Postgresql MCP
A PostgreSQL database MCP service based on the FastMCP library, providing CRUD operations, schema inspection, and custom SQL query functions for specified tables.
Python
147
4 points
M
MCP Scan
MCP-Scan is a security scanning tool for MCP servers, used to detect common security vulnerabilities such as prompt injection, tool poisoning, and cross-domain escalation.
Python
658
5 points
Featured MCP Services
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
150
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
199
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.8K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
889
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
613
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
332
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
795
4.8 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2025AIbase