Sci Hub MCP Server
S

Sci Hub MCP Server

The Sci-Hub MCP service is a bridge connecting AI assistants with Sci-Hub's academic resources, providing functions such as paper search, metadata acquisition, and PDF download through the Model Context Protocol.
2.5 points
11.0K

What is Sci-Hub MCP Server?

This is a bridge service connecting AI assistants with Sci-Hub's academic resources, enabling AI to help you search for, obtain, and analyze academic papers. You can access millions of research papers through simple dialogue instructions.

How to use Sci-Hub MCP Server?

Simply install and configure this service in a supported AI assistant (such as Claude), and then you can search for and obtain papers through natural language instructions. No technical background is required; it's as simple as having a conversation.

Applicable scenarios

Suitable for academic researchers, students, and professionals who need scientific research literature. It is especially useful when you need to quickly obtain literature in a specific field or a specific paper.

Main functions

DOI search
Precisely find a specific paper through the paper's unique identifier (Digital Object Identifier)
Title search
Find relevant literature using the full name or part of the paper's title
Keyword search
Discover relevant papers through keywords in the research field
Metadata acquisition
Obtain detailed information such as the paper's title, author, and publication date
PDF download
Directly download the full-text PDF of the paper (when available)
Advantages
A simple and easy-to-use natural language interface
Fast access to a vast amount of academic resources
Support for multiple search methods (DOI/title/keyword)
Seamless integration with AI assistants
Limitations
Dependence on the availability of the Sci-Hub service
Some of the latest papers may not be available
Requires configuration of the MCP server environment

How to use

Installation preparation
Ensure that Python 3.10+ and the FastMCP library are installed
Get the service code
Clone the GitHub repository to your local machine
Install dependencies
Install the required Python libraries
Configure the AI assistant
Add the MCP server settings to the AI assistant's configuration file (refer to the configuration example in the README)
Start the service
Run the main program to start providing the service

Usage examples

Find a specific paper
When you know the DOI number of a paper, you can directly obtain it
Explore a research field
When you want to know the latest progress in a certain research topic
Obtain the full text of a paper
When you need to read the complete content of a paper

Frequently Asked Questions

Is it legal to use this service?
Why can't some papers be found?
Is there a fee?
Which AI assistants are supported?

Related resources

GitHub repository
Project source code and the latest updates
FastMCP documentation
Official documentation for the MCP protocol
Python official website
The official website of the Python programming language

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "scihub": {
      "command": "python",
      "args": ["-m", "sci_hub_server.py"]
      }
  }
}

{
  "mcpServers": {
    "scihub": {
      "command": "C:\\Users\\YOUR\\PATH\\miniconda3\\envs\\mcp_server\\python.exe",
      "args": [
        "D:\\code\\YOUR\\PATH\\Sci-Hub-MCP-Server\\sci_hub_server.py"
      ],
      "env": {},
      "disabled": false,
      "autoApprove": []
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

P
Praisonai
PraisonAI is a production-ready multi-AI agent framework with self-reflection capabilities, designed to create AI agents to automate the solution of various problems from simple tasks to complex challenges. It simplifies the construction and management of multi-agent LLM systems by integrating PraisonAI agents, AG2, and CrewAI into a low-code solution, emphasizing simplicity, customization, and effective human-machine collaboration.
Python
7.4K
5 points
H
Haiku.rag
Haiku RAG is an intelligent retrieval - augmented generation system built on LanceDB, Pydantic AI, and Docling. It supports hybrid search, re - ranking, Q&A agents, multi - agent research processes, and provides local - first document processing and MCP server integration.
Python
5.1K
5 points
C
Claude Context
Claude Context is an MCP plugin that provides in - depth context of the entire codebase for AI programming assistants through semantic code search. It supports multiple embedding models and vector databases to achieve efficient code retrieval.
TypeScript
15.0K
5 points
M
Maverick MCP
MaverickMCP is a personal stock analysis server based on FastMCP 2.0, providing professional level financial data analysis, technical indicator calculation, and investment portfolio optimization tools for MCP clients such as Claude Desktop. It comes pre-set with 520 S&P 500 stock data, supports multiple technical analysis strategies and parallel processing, and can run locally without complex authentication.
Python
10.3K
4 points
A
Acemcp
Acemcp is an MCP server for codebase indexing and semantic search, supporting automatic incremental indexing, multi-encoding file processing, .gitignore integration, and a Web management interface, helping developers quickly search for and understand code context.
Python
14.7K
5 points
K
Klavis
Klavis AI is an open-source project that provides a simple and easy-to-use MCP (Model Context Protocol) service on Slack, Discord, and Web platforms. It includes various functions such as report generation, YouTube tools, and document conversion, supporting non-technical users and developers to use AI workflows.
TypeScript
17.3K
5 points
M
MCP
The Microsoft official MCP server provides search and access functions for the latest Microsoft technical documentation for AI assistants
13.2K
5 points
S
Scrapling
Scrapling is an adaptive web scraping library that can automatically learn website changes and re - locate elements. It supports multiple scraping methods and AI integration, providing high - performance parsing and a developer - friendly experience.
Python
13.1K
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
30.4K
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
63.1K
4.3 points
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
21.1K
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
18.2K
4.5 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
58.4K
4.5 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#
27.2K
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
19.0K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
85.7K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase