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
13

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 searchSupports keyword search and filtering conditions (such as date range, subject category) to help users quickly locate the required papers.
Paper downloadDownload complete papers directly from arXiv and save them to the local storage directory.
Paper list viewingList all downloaded papers for easy management and reference.
Local storagePapers are automatically saved on the local disk to improve subsequent access speed.
Research prompt generationProvide a series of preset research topics or questions to stimulate users' creativity.

Advantages and limitations

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 papersThe user wants to find new papers in the field of artificial intelligence published in the last three months.
Case title: Download a specific paperThe 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.
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
343
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
830
4.3 points
M
MCP Server Airbnb
Certified
MCP service for Airbnb listing search and details query
TypeScript
248
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
324
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
111
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
616
5 points
A
Agentic Radar
Agentic Radar is a security scanning tool for analyzing and assessing agentic systems, helping developers, researchers, and security experts understand the workflows of agentic systems and identify potential vulnerabilities.
Python
556
5 points
C
Cloudflare
Changesets is a build tool for managing versions and releases in multi - package or single - package repositories.
TypeScript
1.5K
5 points
Featured MCP Services
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
141
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
86
4.3 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
1.7K
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
830
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#
566
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
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
754
4.8 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
5.2K
4.7 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2025AIbase