Navigation
MCP Scholarly Server: Precision Search & Trusted Insights - MCP Implementation

MCP Scholarly Server: Precision Search & Trusted Insights

MCP Scholarly Server: Instantly find precise academic articles, trusted by researchers for fast, accurate, and reliable insights. #SearchSmarter

Research And Data
4.2(101 reviews)
151 saves
70 comments

This tool saved users approximately 10997 hours last month!

About MCP Scholarly Server

What is MCP Scholarly Server: Precision Search & Trusted Insights?

MCP Scholarly Server is a specialized tool designed to help researchers, educators, and professionals quickly access accurate academic articles. It leverages the Model Context Protocol (MCP) framework to streamline scholarly searches, starting with Arxiv integration and expanding to include more platforms in the future. This server ensures reliable results while maintaining user-centric simplicity.

How to Use MCP Scholarly Server: Precision Search & Trusted Insights?

Getting started is straightforward:

  1. Install via Smithery: Run npx -y @smithery/cli install mcp-scholarly --client claude for automatic setup on Claude Desktop.
  2. Configure Manually: Adjust claude_desktop_config.json to specify server paths or use Docker with docker run --rm -i mcp/scholarly.
  3. Search: Use the search-arxiv tool with a keyword to retrieve relevant papers instantly.

MCP Scholarly Server Features

Key Features of MCP Scholarly Server: Precision Search & Trusted Insights?

  • Targeted Search: The search-arxiv tool prioritizes precision, requiring only a keyword to fetch structured results.
  • Expandable Ecosystem: Built for future integration with additional academic databases, ensuring long-term relevance.
  • Developer-Friendly: Easy configuration options and debug tools like MCP Inspector simplify troubleshooting.

Use Cases of MCP Scholarly Server: Precision Search & Trusted Insights?

MCP Scholarly Server FAQ

FAQ from MCP Scholarly Server: Precision Search & Trusted Insights?

Does it support platforms beyond Arxiv?
Yes—future updates will add more sources. Subscribe to release notes for updates.
Can I debug errors easily?
Use the MCP Inspector tool for real-time analysis of search queries and server responses.
Is there a GUI option?
Currently CLI-focused, but API endpoints allow integration with custom interfaces.

Content

mcp-scholarly MCP server

smithery badge

A MCP server to search for accurate academic articles. More scholarly vendors will be added soon.

demo1.jpeg

image

Scholarly Server MCP server

star-history-2025323

Components

Tools

The server implements one tool:

  • search-arxiv: Search arxiv for articles related to the given keyword.
    • Takes "keyword" as required string arguments

Quickstart

Install

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

Development/Unpublished Servers Configuration
"mcpServers": {
  "mcp-scholarly": {
    "command": "uv",
    "args": [
      "--directory",
      "/Users/adityakarnam/PycharmProjects/mcp-scholarly/mcp-scholarly",
      "run",
      "mcp-scholarly"
    ]
  }
}
Published Servers Configuration
"mcpServers": {
  "mcp-scholarly": {
    "command": "uvx",
    "args": [
      "mcp-scholarly"
    ]
  }
}

or if you are using Docker

Published Docker Servers Configuration
"mcpServers": {
  "mcp-scholarly": {
    "command": "docker",
    "args": [
      "run", "--rm", "-i",
      "mcp/scholarly"
    ]
  }
}

Installing via Smithery

To install mcp-scholarly for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install mcp-scholarly --client claude

Development

Building and Publishing

To prepare the package for distribution:

  1. Sync dependencies and update lockfile:
uv sync
  1. Build package distributions:
uv build

This will create source and wheel distributions in the dist/ directory.

  1. Publish to PyPI:
uv publish

Note: You'll need to set PyPI credentials via environment variables or command flags:

  • Token: --token or UV_PUBLISH_TOKEN
  • Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory /Users/adityakarnam/PycharmProjects/mcp-scholarly/mcp-scholarly run mcp-scholarly

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

Related MCP Servers & Clients