academia_mcp

Overview

The Academia MCP server is a comprehensive Python-based tool designed to automate scientific research workflows. It integrates with multiple academic platforms including ArXiv, ACL Anthology, Hugging Face, and Semantic Scholar, as well as web search engines. The server offers features like paper search, PDF download and reading, LaTeX compilation, and optional LLM-powered document QA and research proposal generation. It supports multiple transport protocols (stdio, sse, streamable-http) and includes token-based authentication for secure deployment in production environments.

Try asking AI

After installing, here are 6 things you can ask your AI assistant:

• arxiv_search

  Query arXiv with field-specific queries and filters.

  Try:Find recent machine learning papers about transformersTry:Search for papers in computer vision from 2022 to 2023
• arxiv_download

  Fetch a paper by ID and convert to structured text.

  Try:Download paper 2310.05217 from arXivTry:Get HTML version of paper 1807.03843
• anthology_search

  Search ACL Anthology with fielded queries and date filtering.

  Try:Find papers about NLP in ACL AnthologyTry:Search for machine learning papers from 2020
• hf_datasets_search

  Find Hugging Face datasets with filters and sorting.

  Try:Search for datasets about natural language processingTry:Find computer vision datasets with more than 1000 samples
• s2_get_citations

  List papers citing a given arXiv paper from Semantic Scholar.

  Try:Find papers that cite 2306.11646Try:Get citations for paper 1810.04805
• s2_get_references

  List papers referenced by a given arXiv paper.

  Try:Show references for paper 2306.11646Try:Find references of paper 1810.04805
• visit_webpage

  Fetch and normalize a web page.

  Try:Visit https://arxiv.org/abs/2306.11646 and summarizeTry:Extract content from https://aclanthology.org/
• web_search

  Unified search wrapper using configured search providers.

  Try:Search for recent developments in quantum computingTry:Find papers about transformer architectures
• compile_latex

  Compile LaTeX to PDF in WORKSPACE_DIR.

  Try:Compile my paper.tex to PDFTry:Build research document from LaTeX source
• read_pdf

  Extract text per page from a PDF.

  Try:Read content of paper.pdfTry:Extract text from research_document.pdf
• document_qa

  Answer questions over provided document chunks using LLM.

  Try:What are the main findings in this document?Try:Summarize the key points of this paper
• generate_research_proposals

  Generate research proposals using LLM.

  Try:Generate a research proposal for neural architecture searchTry:Create a proposal for studying climate change impacts

Comparable tools

Installation

pip3 install academia-mcp

uv venv .venv
make install

python -m academia_mcp --transport streamable-http

python -m academia_mcp --transport stdio

{
  "mcpServers": {
    "academia": {
      "command": "python3",
      "args": [
        "-m",
        "academia_mcp",
        "--transport",
        "stdio"
      ]
    }
  }
}

FAQ

Which academic databases does this server support?

The server supports ArXiv, ACL Anthology, Hugging Face datasets, and Semantic Scholar citations and references.

How do I enable LLM-powered features like document QA?

Set the OPENROUTER_API_KEY environment variable to enable LLM-based tools like document_qa and research proposal helpers.

Does it support LaTeX compilation?

Yes, the server includes tools for LaTeX compilation and templates, but requires a LaTeX distribution to be installed on your system.

Compare academia_mcp with