Happy slice of mcp pizzaMCP.pizza

academic-search-mcp-server

MCP.Pizza Chef: afrise

Three tools are on offer: a topic search with an optional year range, a general search, and a look-up of one paper by its identifier. Only the topic search returns what the notes promise. The general search asks Semantic Scholar for the wrong thing and silently drops every result from it, so you get bare Crossref entries with no abstracts. The look-up defaults to Semantic Scholar even though the notes say Crossref. No key is needed or accepted, and the free Semantic Scholar tier is often busy. Untouched since February 2025.

Unmaintained · No commits in 19 months.
Web/Research

Use This MCP server To

Find papers on a topic published between two years Look up one paper by its DOI Get the plain-language summary of a paper Check whether a paper is free to read Collect titles and authors for a reading list

README

Academic Paper Search MCP Server

smithery badge

A Model Context Protocol (MCP) server that enables searching and retrieving academic paper information from multiple sources.

The server provides LLMs with:

  • Real-time academic paper search functionality
  • Access to paper metadata and abstracts
  • Ability to retrieve full-text content when available
  • Structured data responses following the MCP specification

While primarily designed for integration with Anthropic's Claude Desktop client, the MCP specification allows for potential compatibility with other AI models and clients that support tool/function calling capabilities (e.g. OpenAI's API).

Note: This software is under active development. Features and functionality are subject to change.

Academic Paper Search Server MCP server

Features

This server exposes the following tools:

  • search_papers: Search for academic papers across multiple sources

    • Parameters:
      • query (str): Search query text
      • limit (int, optional): Maximum number of results to return (default: 10)
    • Returns: Formatted string containing paper details

  • fetch_paper_details: Retrieve detailed information for a specific paper

    • Parameters:
      • paper_id (str): Paper identifier (DOI or Semantic Scholar ID)
      • source (str, optional): Data source ("crossref" or "semantic_scholar", default: "crossref")
    • Returns: Formatted string with comprehensive paper metadata including:
      • Title, authors, year, DOI
      • Venue, open access status, PDF URL (Semantic Scholar only)
      • Abstract and TL;DR summary (when available)

  • search_by_topic: Search for papers by topic with optional date range filter

    • Parameters:
      • topic (str): Search query text (limited to 300 characters)
      • year_start (int, optional): Start year for date range
      • year_end (int, optional): End year for date range
      • limit (int, optional): Maximum number of results to return (default: 10)
    • Returns: Formatted string containing search results including:
      • Paper titles, authors, and years
      • Abstracts and TL;DR summaries when available
      • Venue and open access information

Setup

Installing via Smithery

To install Academic Paper Search Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @afrise/academic-search-mcp-server --client claude

academic-search-mcp-server FAQ

Do I need an API key?
No, and it will not use one even if you set it. The setup notes list two key settings and then admit in a comment that neither is implemented, so every request goes out unregistered.
Which of the three searches should I use?
The topic search. It is the only one that comes back with abstracts and plain-language summaries. The general search quietly loses everything Semantic Scholar sends and leaves you with titles, authors, years and links.
Why do my searches keep coming back empty?
The free Semantic Scholar tier is shared and frequently answers with a too-many-requests refusal, which happened when this was checked. The server hides every failure behind one generic message, and because it cannot use a key, waiting is your only option.
Can I use this to read the full text of a paper?
No. Where a free copy exists you get a link to it, plus title, authors, year and abstract. Nothing is ever downloaded.
Does the Claude Desktop snippet in the notes work?
Watch for a stray space in the command it passes along, which some setups reject outright. Removing it fixes a mysterious startup failure.
Which apps does it work in?
Claude Desktop is the documented one. A Smithery install is listed, but the author says on the page that it is largely untested and their service was having trouble.
Is it still maintained?
It describes itself as under active development, but nothing has changed since February 2025, roughly a year and a half ago.
Can I use this at work?
It carries the AGPL version 3, the strictest of the common licences. If you build it into anything you offer to other people over a network, you have to publish your source too. Check with whoever handles licensing.