playbooks

home / mcp / paper search mcp server

Paper Search MCP Server

A MCP for searching and downloading academic papers from multiple sources like arXiv, PubMed, bioRxiv, etc.

Installation
Add the following to your MCP client configuration file.

Configuration

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

You can run the Paper Search MCP server locally to search and download academic papers from multiple sources, including arXiv, PubMed, bioRxiv, and Semantic Scholar. It integrates with MCP clients to provide papers in a consistent format for use in large language model workflows.

How to use

You run the server on your workstation and connect your MCP client to it. The server exposes tools to search for papers across supported platforms and to download PDFs when needed. Use it to build context for your LLMs, enrich responses with up-to-date literature, and fetch papers on demand for study or citation.

How to install

Prerequisites: you need Python installed and a working MCP client environment. You will also use the UV runtime to run the server locally.

Step 1: Install the package manager for local MCP servers if you do not already have it.

uv add paper-search-mcp

Step 2: Prepare the runtime configuration for your MCP client. Create a configuration that points to the local server and the start command shown in the following example.

Step 3: Start the server via the MCP runtime. The configuration below runs the server from your installation path and uses the paper_search_mcp.server entry point.

{
  "mcpServers": {
    "paper_search_mcp": {
      "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
      }
    }
  }
}

Configuration and usage notes

The standard start command runs the server locally via the MCP runtime. You can customize the directory path to point to where you installed the server code. If you need Semantic Scholar enhancements, provide an API key; otherwise you can omit it.

Security and environment considerations

Keep API keys and credentials out of your codebase. Use environment hygiene to manage any API keys and restrict server access to trusted clients within your organization.

Available tools

search_arxiv

Search arXiv for papers using queries, filters, and return results in a standardized format.

download_arxiv

Download the PDF for a selected arXiv paper by its identifier.