Ilyagusev Academia_mcp
by ai.smitherycommunityv1.16.0
82
6
Academia MCP is a server that provides tools to search, fetch, analyze, and report on scientific papers and datasets.
From the registry: Search arXiv and ACL Anthology, retrieve citations and references, and browse web sources to accel…
Install & configure
Prerequisites
- requiredPython 3.12+Required Python version
- requiredacademia-mcp packageInstall via pip
https://pypi.org/project/academia-mcp/$ pip3 install academia-mcp
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `ilyagusev-academia_mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Python 3.12+** — Required Python version
- **academia-mcp package** — Install via pip Run: `pip3 install academia-mcp` (https://pypi.org/project/academia-mcp/)
Canonical MCP server config (stdio transport):
- command: `python3`
- args: ["-m","academia_mcp","--transport","stdio"]
- optional environment variables:
- `OPENROUTER_API_KEY`: Required for LLM-related tools (document_qa, review_pdf_paper, bitflip tools) (example: `<your-openrouter-api-key>`)
- `EXA_API_KEY`: Enables Exa web search and visit_webpage tool (example: `<your-exa-api-key>`)
- `BRAVE_API_KEY`: Enables Brave web search (example: `<your-brave-api-key>`)
- `TAVILY_API_KEY`: Enables Tavily web search (example: `<your-tavily-api-key>`)
- `WORKSPACE_DIR`: Directory for generated files; enables compile_latex, read_pdf, download_pdf_paper, and review_pdf_paper tools (example: `/path/to/workspace`)
Note: MCP server for academic research: ArXiv, ACL Anthology, Hugging Face datasets, Semantic Scholar citations, web search, LaTeX compilation, PDF reading, and optional LLM-powered tools. HTTP/SSE transport also supported by passing --transport streamable-http or --transport sse.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: MCP server for academic research: ArXiv, ACL Anthology, Hugging Face datasets, Semantic Scholar citations, web search, LaTeX compilation, PDF reading, and optional LLM-powered tools. HTTP/SSE transport also supported by passing --transport streamable-http or --transport sse.
Tools (11)
arxiv_search
Query arXiv with field-specific queries and filters.
arxiv_download
Fetch a paper by ID and convert to structured text (HTML/PDF modes).
anthology_search
Search ACL Anthology with fielded queries and optional date filtering.
hf_datasets_search
Find Hugging Face datasets with filters and sorting.
s2_get_citations
List papers citing a given arXiv paper (Semantic Scholar Graph).
s2_get_references
List papers referenced by a given arXiv paper.
visit_webpage
Fetch and normalize a web page.
web_search
Unified search wrapper; available when at least one of Exa/Brave/Tavily keys is set.
compile_latex
Compile LaTeX to PDF in WORKSPACE_DIR.
read_pdf
Extract text per page from a PDF.
document_qa
Answer questions over provided document chunks (requires LLM).
Environment variables
OPENROUTER_API_KEYrequiredRequired for LLM-related tools.Prerequisites
- • Python 3.12+
- • python3
Remote Endpoints
https://server.smithery.ai/@IlyaGusev/academia_mcp/mcp
type: streamable-http
Details
- Language
- Python
- License
- Apache-2.0
- Released
- Oct 2, 2025
- Last commit
- Jan 25, 2026
- Registry name
- ai.smithery/IlyaGusev-academia_mcp