AIBase
EN
Explore
Arxiv MCP
A

Arxiv MCP

The ArXiv MCP Server is a middleware that provides arXiv paper search and access services for AI assistants, implementing paper retrieval, download, and reading functions through the MCP protocol.
Research and dataDeveloper tools#Paper search#AI tool#Research assistance.Python
2.5 points
8.7K
Open Site

Overview

Installation

Content Details

Alternatives

What is the ArXiv MCP Server?

The ArXiv MCP Server is a tool that allows AI assistants to search for and access research papers on arXiv through a simple method. This server is implemented through the Message Control Protocol (MCP), enabling AI to efficiently search for and obtain academic resources.

How to use the ArXiv MCP Server?

You can start using the ArXiv MCP Server in just a few steps. First, install the server, then add the corresponding settings to the client configuration file, and finally, you can start querying and downloading papers.

Applicable scenarios

This server is very suitable for researchers and students who need to quickly retrieve and manage a large number of academic papers. Whether you are looking for the latest progress in a specific field or reviewing classic literature, ArXiv MCP can meet your needs.

Main features

Paper search
Supports keyword search and filtering conditions (such as date range, subject category) to help users quickly locate the required papers.
Paper download
Download complete papers directly from arXiv and save them to the local storage directory.
Paper list viewing
List all downloaded papers for easy management and reference.
Local storage
Papers are automatically saved on the local disk to improve subsequent access speed.
Research prompt generation
Provide a series of preset research topics or questions to stimulate users' creativity.
Advantages
Powerful search function supporting multiple filtering conditions.
Local storage accelerates the subsequent usage experience.
Open - source and easy to integrate into existing systems.
Rich API interfaces facilitate secondary development.
Limitations
It depends on the openness of the arXiv database, and some restricted content may not be available.
For very large datasets, the initial loading time is long.
A certain technical background is required to complete the initial deployment.

How to use

Install the ArXiv MCP Server
It can be installed through the Smithery tool or by manually cloning the code repository.
Configure the client
Edit the client configuration file and add the relevant settings for the ArXiv MCP Server.
Start using
After starting the server, you can perform operations such as searching and downloading.

Usage examples

Case title: Find the latest artificial intelligence papers
The user wants to find new papers in the field of artificial intelligence published in the last three months.
Case title: Download a specific paper
The user needs to download a classic paper on reinforcement learning.

Frequently Asked Questions

How can I ensure that my papers will not be lost?
Does it support cross - platform operation?
Can I customize the storage path?

Related resources

Official documentation
Detailed installation guide and technical documentation.
GitHub code repository
Source code address and contribution guide.
Demo video
Watch how to quickly get started with the ArXiv MCP Server.

Installation

Copy the following command to your Client for configuration
{
    "mcpServers": {
        "arxiv-mcp-server": {
            "command": "uv",
            "args": [
                "tool",
                "run",
                "arxiv-mcp-server",
                "--storage-path", "/path/to/paper/storage"
            ]
        }
    }
}

{
    "mcpServers": {
        "arxiv-mcp-server": {
            "command": "uv",
            "args": [
                "--directory",
                "path/to/cloned/arxiv-mcp-server",
                "run",
                "arxiv-mcp-server",
                "--storage-path", "/path/to/paper/storage"
            ]
        }
    }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

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
8.2K
5 points
B
Blueprint MCP
Blueprint MCP is a chart generation tool based on the Arcade ecosystem. It uses technologies such as Nano Banana Pro to automatically generate visual charts such as architecture diagrams and flowcharts by analyzing codebases and system architectures, helping developers understand complex systems.
Python
6.5K
4 points
M
MCP Agent Mail
MCP Agent Mail is a mail - based coordination layer designed for AI programming agents, providing identity management, message sending and receiving, file reservation, and search functions, supporting asynchronous collaboration and conflict avoidance among multiple agents.
Python
9.4K
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
13.5K
5 points
M
MCP
The Microsoft official MCP server provides search and access functions for the latest Microsoft technical documentation for AI assistants
12.7K
5 points
A
Aderyn
Aderyn is an open - source Solidity smart contract static analysis tool written in Rust, which helps developers and security researchers discover vulnerabilities in Solidity code. It supports Foundry and Hardhat projects, can generate reports in multiple formats, and provides a VSCode extension.
Rust
10.6K
5 points
D
Devtools Debugger MCP
The Node.js Debugger MCP server provides complete debugging capabilities based on the Chrome DevTools protocol, including breakpoint setting, stepping execution, variable inspection, and expression evaluation.
TypeScript
9.9K
4 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
11.5K
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
27.0K
5 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
16.4K
4.5 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
19.1K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
52.9K
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#
22.7K
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
51.3K
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
18.1K
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
34.9K
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