Skip to main content
Glama
ArXiv MCP Server
by wr-web

Twitter Follow Python Version Tests License: MIT PyPI Downloads PyPI Version

ArXiv MCP Server

๐Ÿ” Enable AI assistants to search and access arXiv papers through a simple MCP interface.

The ArXiv MCP Server provides a bridge between AI assistants and arXiv's research repository through the Model Context Protocol (MCP). It allows AI models to search for papers and access their content in a programmatic way.

๐Ÿค Contribute โ€ข ๐Ÿ“ Report Bug

โœจ Core Features

  • ๐Ÿ”Ž Paper Search: Query arXiv papers with filters for date ranges and categories

  • ๐Ÿ“„ Paper Access: Download and read paper content

  • ๐Ÿ“‹ Paper Listing: View all downloaded papers

  • ๐Ÿ—ƒ๏ธ Local Storage: Papers are saved locally for faster access

  • ๐Ÿ“ Prompts: A Set of Research Prompts

Related MCP server: ArXiv Paper MCP

๐Ÿš€ Quick Start

Installing via Smithery

To install ArXiv Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install arxiv-mcp-server --client claude

Installing Manually

Install using uv:

uv tool install arxiv-mcp-server

For development:

# Clone and set up development environment
git clone https://github.com/blazickjp/arxiv-mcp-server.git
cd arxiv-mcp-server

# Create and activate virtual environment
uv venv
source .venv/bin/activate

# Install with test dependencies
uv pip install -e ".[test]"

๐Ÿ”Œ MCP Integration

Add this configuration to your MCP client config file:

{
    "mcpServers": {
        "arxiv-mcp-server": {
            "command": "uv",
            "args": [
                "tool",
                "run",
                "arxiv-mcp-server",
                "--storage-path", "/path/to/paper/storage"
            ]
        }
    }
}

For Development:

{
    "mcpServers": {
        "arxiv-mcp-server": {
            "command": "uv",
            "args": [
                "--directory",
                "path/to/cloned/arxiv-mcp-server",
                "run",
                "arxiv-mcp-server",
                "--storage-path", "/path/to/paper/storage"
            ]
        }
    }
}

๐Ÿ’ก Available Tools

The server provides four main tools:

Search for papers with optional filters:

result = await call_tool("search_papers", {
    "query": "transformer architecture",
    "max_results": 10,
    "date_from": "2023-01-01",
    "categories": ["cs.AI", "cs.LG"]
})

2. Paper Download

Download a paper by its arXiv ID:

result = await call_tool("download_paper", {
    "paper_id": "2401.12345"
})

3. List Papers

View all downloaded papers:

result = await call_tool("list_papers", {})

4. Read Paper

Access the content of a downloaded paper:

result = await call_tool("read_paper", {
    "paper_id": "2401.12345"
})

๐Ÿ“ Research Prompts

The server offers specialized prompts to help analyze academic papers:

Paper Analysis Prompt

A comprehensive workflow for analyzing academic papers that only requires a paper ID:

result = await call_prompt("deep-paper-analysis", {
    "paper_id": "2401.12345"
})

This prompt includes:

  • Detailed instructions for using available tools (list_papers, download_paper, read_paper, search_papers)

  • A systematic workflow for paper analysis

  • Comprehensive analysis structure covering:

    • Executive summary

    • Research context

    • Methodology analysis

    • Results evaluation

    • Practical and theoretical implications

    • Future research directions

    • Broader impacts

โš™๏ธ Configuration

Configure through environment variables:

Variable

Purpose

Default

ARXIV_STORAGE_PATH

Paper storage location

~/.arxiv-mcp-server/papers

๐Ÿงช Testing

Run the test suite:

python -m pytest

๐Ÿ“„ License

Released under the MIT License. See the LICENSE file for details.


Made with โค๏ธ by the Pearl Labs Team

Available Tools

4 tools
download_paperC

Download a paper and create a resource for it

Inputs: paper_id (required), check_status.

list_papersA

List all existing papers available as resources

Inputs: no named parameters.

read_paperC

Read the full content of a stored paper in markdown format

Inputs: paper_id (required).

search_papersC

Search for papers on arXiv with advanced filtering

Inputs: query (required), max_results, date_from, date_to, +3 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelogโ€ฆ

    TDQS

    B3.4/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a distinct and clear purpose: download_paper fetches new papers, list_papers shows existing resources, read_paper accesses stored content, and search_papers finds papers on arXiv. There is no overlap in functionality, making tool selection straightforward for an agent.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with snake_case (e.g., download_paper, list_papers, read_paper, search_papers). This uniformity enhances readability and predictability across the tool set.

    Tool Count4/5

    With 4 tools, the count is appropriate for a focused arXiv server, covering core operations like search, download, list, and read. It's slightly lean but reasonable; adding tools for metadata management or updates could improve coverage without being excessive.

    Completeness4/5

    The tool set covers essential arXiv workflows: searching, downloading, listing, and reading papers. Minor gaps exist, such as lacking tools for updating or deleting stored papers, but agents can still perform key tasks effectively within the domain.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      Enables AI assistants to search and access arXiv research papers through a simple Message Control Protocol interface, allowing for paper search, download, listing, and reading capabilities.
      4
      7
      Apache 2.0
    • A
      license
      B
      quality
      C
      maintenance
      Provides paper search, PDF link retrieval, and content parsing for arXiv research papers, enabling seamless access to scientific literature through the Model Context Protocol.
      4
      41 npm
      24
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to search, retrieve, analyze, and export academic papers from arXiv.org using the Model Context Protocol.
      19
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables AI assistants to search, download, and access arXiv papers with local storage and date filtering via the Model Context Protocol.
      3
      1
      Apache 2.0