# scholar [Health: Active]

**Category:** 🔬 Research  
**Repository:** https://github.com/mlintangmz2765/Scholar-MCP  
**GitHub Stars:** 0  
**Views:** 1  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/scholar

## Description
Hardened Scholar MCP for deep academic research (Scopus, OpenAlex, Unpaywall) with PDF vision.

## Tools
Capabilities this server exposes over MCP:

- **search_papers_tool** — Search papers via Scopus (Boolean syntax) or OpenAlex. Sort by `cited_by_count` or `publication_year`.
- **search_papers_s2_tool** — Search papers via Semantic Scholar. Note: strictly rate-limited to 1 request/sec.
- **get_paper_details_tool** — Fetch full metadata and abstract by Scopus ID, DOI, or OpenAlex ID (with automatic routing).
- **get_paper_details_s2_tool** — Fetch full metadata from Semantic Scholar, including **AI-generated TLDRs**. Accepts S2 ID or DOI.
- **search_titles_unpaywall_tool** — Search Unpaywall's database directly by title. Set `is_oa=True` for strictly OA results.
- **get_related_works_tool** — Find related/similar papers using OpenAlex's bibliographic coupling.
- **search_books_tool** — Search for book metadata via Google Books or Open Library.
- **get_book_details_tool** — Fetch complete book details, descriptions, and ISBNs.
- **search_libgen_tool** — Search Library Genesis for books to retrieve their download MD5 hashes.
- **interact_with_book_tool** — Smart extraction from Libgen. Actions: `toc` (Table of Contents), `search` (keywords), `pages` (range).
- **autocomplete_authors_tool** — Rapidly disambiguate author names and resolve OpenAlex Author IDs.
- **search_authors_tool** — Detailed bibliometric profiles: H-index, i10-index, ORCID, and research concepts.
- **search_author_by_orcid_tool** — Look up an author directly by ORCID (raw or URL format).
- **retrieve_author_works_tool** — Chronologically sorted publications for a given OpenAlex author.
- **get_author_profile_scopus_tool** — Fetch precise Scopus-sourced h-index, citation counts, and affiliation.
- **get_author_profile_s2_tool** — Fetch Semantic Scholar author profile (H-index, paper count, citations).
- **get_citations_tool** — Retrieve forward citations or backward references via OpenAlex.
- **get_full_text_tool** — Extract text from an OA PDF or HTML page. Supports page range selection.
- **get_full_text_visual_tool** — Render PDF pages as images for Vision-capable LLMs.
- **fetch_pdf_text_unpaywall_tool** — All-in-one: resolve DOI via Unpaywall → download PDF → extract text.
- **get_scihub_link_tool** — Attempts to resolve a strict paywalled DOI to a free direct PDF link using Sci-Hub.
- **fetch_pdf_text_scihub_tool** — All-in-one bypass: resolve DOI via Sci-Hub → download PDF → extract text.
- **get_bibtex_tool** — Generate a BibTeX entry for LaTeX via CrossRef content negotiation.
- **format_citation_tool** — Format citation in APA, IEEE, Chicago, Harvard, Vancouver, MLA, or Turabian.
- **get_unpaywall_link_tool** — Resolve a DOI to all available OA locations via Unpaywall.
- **search_topics_tool** — Browse research topics/concepts. Returns fields, domains, and publication volume.
- **batch_lookup_tool** — Batch-fetch metadata for multiple DOIs in a single call (max 50).

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `uvx` (confidence: high):

```json
"mcpServers": {
  "scholar": {
    "command": "uvx",
    "args": ["scholar-academic-mcp"],
    "env": {
      "SCOPUS_API_KEY": "",
      "S2_API_KEY": "",
      "SCIHUB_MIRRORS": "",
      "LIBGEN_MIRRORS": "",
      "SCOPUS_INST_TOKEN": "",
      "CONTACT_EMAIL": ""
    }
  }
}
```

**Requires environment variables:** `SCOPUS_API_KEY`, `S2_API_KEY`, `SCIHUB_MIRRORS`, `LIBGEN_MIRRORS`, `SCOPUS_INST_TOKEN`, `CONTACT_EMAIL` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What scholar does

The scholar MCP server exposes academic research and book-retrieval functions through the Model Context Protocol. It gives an AI agent access to paper search, paper metadata, author identification, bibliometric profiles, citation relationships, topic exploration, book metadata, and document-content extraction.

Paper searches can use Scopus Boolean queries or OpenAlex, with sorting by citation count or publication year. Semantic Scholar provides a separate search path and can return AI-generated TLDRs when configured. Metadata lookup accepts identifiers such as DOI, Scopus ID, OpenAlex ID, or Semantic Scholar ID, depending on the tool. Batch lookup supports up to 50 DOIs per request.

The server also handles open-access discovery and content processing. It can search Unpaywall by title, resolve DOI locations, download an open-access PDF, extract text, and render PDF pages as images. HTML pages are supported by the full-text extraction path. Book functions cover Google Books, Open Library, and Library Genesis searches, including targeted extraction from retrieved books.

## How it works

An MCP-compatible client starts the server as a local process and sends tool calls over MCP. The server routes requests to external APIs and services, then returns structured results to the agent. Paper and author requests may use different providers based on the identifier or selected search path.

For document analysis, the server checks available access routes, retrieves an accessible PDF or HTML page, and passes content through text or visual extraction. The visual tool renders selected PDF pages as PNG images for models that can inspect images. Closed-access material may require manual handling, according to the project’s access workflow.

The scholar MCP server includes fallback-oriented paths for DOI resolution and PDF retrieval. Its Semantic Scholar search is limited to one request per second. Sci-Hub and Library Genesis tools are included for resolving or retrieving material from those services; their use may have legal, licensing, or policy implications and should be evaluated by the operator.

## Setup and configuration

Install the package from PyPI with `pip install scholar-academic-mcp`, or clone the repository and install it in editable mode with `pip install -e .` inside a virtual environment. The documented client configuration uses the `scholar-academic-mcp` command as a stdio MCP server.

`SCOPUS_API_KEY` and `CONTACT_EMAIL` are required by the documented configuration. `S2_API_KEY` enables Semantic Scholar API access for TLDRs and graph functions. `SCOPUS_INST_TOKEN` is optional and supports fuller Scopus abstract access. `SCIHUB_MIRRORS` and `LIBGEN_MIRRORS` accept comma-separated mirror URLs for their respective retrieval tools.

Claude Desktop and Cursor are explicitly documented as configuration targets. The repository identifies Python 3.10 or newer as the supported Python version.

## Tools and capabilities

- Search papers through Scopus, OpenAlex, or Semantic Scholar.
- Retrieve paper metadata, abstracts, related works, references, and forward citations.
- Resolve authors by name or ORCID and retrieve OpenAlex, Scopus, or Semantic Scholar profiles.
- Explore research topics, domains, concepts, and publication-volume information.
- Search books and retrieve descriptions, editions, and ISBNs.
- Extract book tables of contents, keyword matches, or selected page ranges.
- Extract text from OA PDFs or HTML pages and render PDF pages for visual analysis.
- Generate BibTeX entries and format citations in APA, IEEE, Chicago, Harvard, Vancouver, MLA, or Turabian styles.

## Limitations and notes

Provider coverage and fields depend on the upstream service and the credentials supplied. Scopus features require an API key, Semantic Scholar requests are rate-limited to one per second, and full Scopus abstracts may require an institutional token. Unpaywall focuses on open-access locations, while access to closed material is not guaranteed. The repository also documents a Semantic Scholar API key as optional, but some Semantic Scholar capabilities depend on it.

_Full upstream README: https://allmcps.com/mcp/scholar/readme_