Paper Search

Provides multi-source paper search and download capabilities via MCP, enabling integration with LLMs for literature access.

python

0

GitHub Stars

python

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "morosss-sdfsdf": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/your/paper-search-mcp",
        "-m",
        "paper_search_mcp.server"
      ]
    }
  }
}

Paper Search MCP is a Python-based MCP server that lets you search and download academic papers from multiple sources, enabling seamless integration with large language model workflows and enabling you to retrieve relevant literature efficiently.

How to use

You run the Paper Search MCP alongside your MCP client to perform literature searches and fetch PDFs. Start the local MCP server, then connect your client to it to invoke search and download actions. The server exposes a consistent set of functions that let you search across supported platforms and retrieve paper PDFs for use in your workflows.

How to install

Prerequisites you need before installing: Python installed and a runtime environment ready for Python packages. You also need a tool for managing and running the MCP server locally (the instructions assume you will use uv as shown). Follow the steps below to install and run Paper Search MCP.

# Quick install using uv (no root privileges required)
uv add paper-search-mcp

# Optional: install development tools if you plan to contribute
uv add pytest flake8

Quick start for running locally

Install Package: use the runtime package manager to add the MCP server.

uv add paper-search-mcp

Configure your MCP client (example shown for Claude Desktop). Create or update the following client configuration to point at the local Paper Search MCP instance. Replace the path with your actual installation path.

{
  "mcpServers": {
    "paper_search_server": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/your/paper-search-mcp",
        "-m",
        "paper_search_mcp.server"
      ],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "" // Optional: For enhanced Semantic Scholar features
      }
    }
  }
}

Available tools

search_arxiv

Search papers from the arXiv source and return results in a standardized format.

download_arxiv

Download PDFs from arXiv for a given paper identifier.