Academia MCP

What is Academia MCP?

Academia MCP is a Model Context Protocol server that provides tools to search, fetch, analyze, and report on scientific papers and datasets. It integrates with ArXiv, ACL Anthology, Hugging Face Datasets, Semantic Scholar, web search engines (Exa, Brave, Tavily), and LaTeX compilation. Designed for researchers and developers who want AI-assisted literature discovery and analysis.

How to use Academia MCP?

Install via pip3 install academia-mcp or use uv for development. Run the server with python -m academia_mcp --transport stdio for local MCP clients or --transport streamable-http for HTTP. Configure optional environment variables to enable specific tools (e.g., OPENROUTER_API_KEY for LLM tools, WORKSPACE_DIR for file operations).

Key features of Academia MCP

• ArXiv search and paper download
• ACL Anthology search
• Hugging Face datasets search
• Semantic Scholar citation and reference lookup
• Web search via Exa, Brave, or Tavily
• Web page crawling and PDF reading
• Optional LLM-powered document QA and research proposals
• LaTeX template enumeration and compilation

Use cases of Academia MCP

• Search for recent papers on a specific research topic across multiple databases.
• Retrieve and analyze citations and references for a given arXiv paper.
• Fetch and review PDFs of scientific papers with LLM assistance.
• Generate and score research proposals based on existing literature.
• Compile LaTeX templates into PDFs programmatically.

FAQ from Academia MCP

What are the system requirements for Academia MCP?

Python 3.12 or higher is required. For LaTeX/PDF tools, a LaTeX distribution with pdflatex and latexmk on PATH is needed (e.g., install via sudo apt install texlive-latex-base texlive-fonts-recommended texlive-latex-extra texlive-science latexmk).

How do I enable authentication for HTTP transports?

Set the ENABLE_AUTH environment variable to true and optionally provide a TOKENS_FILE path. Use the academia_mcp auth commands to issue, list, and revoke tokens. Include the token in the Authorization: Bearer <token> header or as the apiKey query parameter.

What environment variables are needed for different tools?

Set OPENROUTER_API_KEY for LLM tools (document_qa, review_pdf_paper, bitflip tools). Set WORKSPACE_DIR for compile_latex, read_pdf, download_pdf_paper, and review_pdf_paper. Set one of EXA_API_KEY, BRAVE_API_KEY, or TAVILY_API_KEY for web search tools.

How do I run Academia MCP with Docker?

Build the image with docker build -t academia_mcp . or use the existing image phoenix120/academia_mcp. Run with docker run -p 5056:5056 -e PORT=5056 -e OPENROUTER_API_KEY=... -e WORKSPACE_DIR=/workspace -v "$PWD/workdir:/workspace" academia_mcp.

What transports are supported?

The server supports three transports: stdio (for local MCP clients like Claude Desktop), sse, and streamable-http. Use the --transport flag to select one. The host/port options apply only to HTTP transports; default port is 5056 (or from PORT environment variable).