Skip to main content
Glama
Scholar MCP Server

Scholar MCP Server

Scholar MCP Server

Python Version Model Context Protocol License: MIT Registry

A Model Context Protocol (MCP) server providing structured access to scientific literature databases. It serves as a unified interface for Scopus, OpenAlex, Semantic Scholar, and Unpaywall, enabling AI agents to perform systematic paper discovery, author disambiguation, citation lineage tracking, and multimodal Content extraction.

Core Capabilities

  • Unified Literature Search

    • Semantic Scholar Integration — High-relevance search and detailed metadata, including AI-generated TLDRs (requires API key).

    • Scopus Integration — Targeted metadata retrieval via advanced Boolean syntax (requires API key).

    • OpenAlex Integration — Broad search across 250M+ works with abstract reconstruction.

    • Unpaywall Resolution — DOI-to-PDF cross-referencing across global Open Access repositories.

    • Sci-Hub Fallback (⚠️ Use with Caution) — Automatic mirror resolution and parsing for paywall bypassing.

  • Book Search & Extraction

    • Google Books & Open Library — Integrated search for book metadata, editions, and descriptions without API keys.

    • Library Genesis (Libgen) — Search and extract full text from books directly using PyMuPDF. Features smart caching and token-saving strategies (TOC reading, targeted keyword searching, and page range extraction).

  • Author Identification & Metrics

    • Instant author disambiguation and ID resolution via OpenAlex autocomplete.

    • Comprehensive profiles: H-index, i10-index, institutional affiliation history, and ORCID linkage.

    • Precision metrics from Elsevier (Scopus) for verified publication counts.

  • Citation Lineage Tracking

    • Map research evolution through forward citations (citing works) and backward references (cited works).

  • Structured & Multimodal Extraction

    • Text Extraction — Layout-aware parsing of OA PDFs using PyMuPDF.

    • Vision Rendering — Page-by-page PNG rendering for LLM-based analysis of charts, tables, and equations.

    • HTML Fallbacks — Extraction from web-based research resources via BeautifulSoup.

  • Topic Mapping & Field Analysis

    • Concepts and domain hierarchy discovery to map research landscapes.

    • Batch metadata retrieval for high-throughput literature processing (up to 50 DOIs/request).

  • Access Management & Fallbacks

    • Automated detection of closed-access content with human-in-the-loop instructions for manual uploads.

Related MCP server: Academic Paper MCP HTTP/SSE Server

Architecture

graph TD
    A[LLM Agent] -->|MCP Protocol| B(Scholar MCP Server)
    B --> C{Database Router}
    C -->|Primary| D[Scopus API]
    C -->|Fallback| E[OpenAlex API]
    C -->|DOI Resolver| F[Unpaywall API]
    C -->|Citations| P[CrossRef API]
    
    D --> G{Access Check}
    E --> G
    F --> G
    P --> G
    
    G -->|Open Access| H[PDF Buffer Download]
    G -->|Closed Access| I[Human-in-the-Loop Prompt]
    H --> J[PyMuPDF Text Extractor]
    H --> K[PyMuPDF Vision Renderer]
    J --> L[Return Context to LLM]
    K --> L
    I --> L
    B --> M{Author Router}
    M -->|Profile| N[OpenAlex Authors API]
    M -->|Metrics| O[Scopus Author API]
    N --> L
    O --> L

Installation

Quick Start (via PyPI)

The fastest way to use the server is directly via PyPI:

pip install scholar-academic-mcp

Manual Setup (for Development)

# Clone the repository
git clone https://github.com/mlintangmz2765/Scholar-MCP.git
cd Scholar-MCP

# Setup virtual environment
python -m venv venv
.\venv\Scripts\activate  # Windows
source venv/bin/activate # Unix

# Install in editable mode
pip install -e .

Environment Variables

Variable

Required

Description

SCOPUS_API_KEY

Yes

Elsevier API key for Scopus search and author retrieval.

S2_API_KEY

No

Semantic Scholar API key for TLDRs and S2 graph access.

SCIHUB_MIRRORS

No

Comma-separated list of active Sci-Hub mirrors for PDF fallback.

LIBGEN_MIRRORS

No

Comma-separated list of active Library Genesis mirrors.

SCOPUS_INST_TOKEN

No

Institutional token for full abstract access via Scopus.

CONTACT_EMAIL

Yes

Email for OpenAlex/Unpaywall polite-pool API routing.

Configuration

Claude Desktop / Cursor

Add the following to your configuration file (e.g., claude_desktop_config.json):

{
  "mcpServers": {
    "scholar-academic-mcp": {
      "command": "scholar-academic-mcp",
      "env": {
        "SCOPUS_API_KEY": "your_scopus_api_key",
        "S2_API_KEY": "your_s2_api_key",
        "SCIHUB_MIRRORS": "https://sci-hub.ru,https://sci-hub.st",
        "LIBGEN_MIRRORS": "https://libgen.la,http://libgen.li",
        "SCOPUS_INST_TOKEN": "your_optional_inst_token",
        "CONTACT_EMAIL": "your_email@domain.com"
      }
    }
  }
}

Quick Start & Examples

Once configured, your AI agent can perform complex research workflows. Below are representative examples of tool inputs and structured outputs.

1. Literature Discovery (Scopus)

Prompt: "Find recent papers about 'Transformer architectures' published after 2022 using Scopus."

Tool Call: search_papers_tool(query="TITLE-ABS-KEY(Transformer architectures) AND PUBYEAR > 2022", limit=3)

Output:

Found 3 papers via Scopus:
- [SCOPUS_ID:85184...] Attention is All You Need? A Survey of Transformer Variants
  Authors: Smith, J., Doe, A.
  Date: 2024-01-15 | DOI: 10.1016/j.artint.2023.104012

2. Multimodal Content Analysis

Prompt: "I need to see the diagram for the neural network architecture on page 3 of this URL."

Tool Call: get_full_text_visual_tool(url="https://arxiv.org/pdf/1706.03762.pdf", max_pages=3)

Output:

  • [Text] "Successfully rendered 3 pages visually..."

  • [Image] (PNG data of page 1)

  • [Image] (PNG data of page 2)

  • [Image] (PNG data of page 3 - containing the architecture diagram)

3. Research Topic Mapping

Prompt: "Help me understand the subfields and domains related to 'Generative AI'."

Tool Call: search_topics_tool(query="Generative AI")

Output:

Found 1 topics for 'Generative AI':
- Artificial Intelligence
  Hierarchy: Computer Science → Artificial Intelligence → Machine Learning
  Works: 12,450 | Citations: 450,210
  Description: A field of computer science that focuses on creating systems capable of generating...

Tools

The server registers 23 tools across 7 categories:

Paper Discovery

Tool

Signature

Description

search_papers_tool

(query, limit=5, use_scopus=True, sort_by="relevance")

Search papers via Scopus (Boolean syntax) or OpenAlex. Sort by cited_by_count or publication_year.

search_papers_s2_tool

(query, limit=5)

Search papers via Semantic Scholar. Note: strictly rate-limited to 1 request/sec.

get_paper_details_tool

(paper_id)

Fetch full metadata and abstract by Scopus ID, DOI, or OpenAlex ID (with automatic routing).

get_paper_details_s2_tool

(paper_id)

Fetch full metadata from Semantic Scholar, including AI-generated TLDRs. Accepts S2 ID or DOI.

search_titles_unpaywall_tool

(query, is_oa=None)

Search Unpaywall's database directly by title. Set is_oa=True for strictly OA results.

get_related_works_tool

(paper_id, limit=10)

Find related/similar papers using OpenAlex's bibliographic coupling.

Book Discovery & Extraction

Tool

Signature

Description

search_books_tool

(query, limit=5, source="googlebooks")

Search for book metadata via Google Books or Open Library.

get_book_details_tool

(book_id, source="googlebooks")

Fetch complete book details, descriptions, and ISBNs.

search_libgen_tool

(query, limit=5)

Search Library Genesis for books to retrieve their download MD5 hashes.

interact_with_book_tool

(md5, action, keyword, start_page, end_page)

Smart extraction from Libgen. Actions: toc (Table of Contents), search (keywords), pages (range).

Author Analytics

Tool

Signature

Description

autocomplete_authors_tool

(name, limit=5)

Rapidly disambiguate author names and resolve OpenAlex Author IDs.

search_authors_tool

(name, institution=None, limit=5)

Detailed bibliometric profiles: H-index, i10-index, ORCID, and research concepts.

search_author_by_orcid_tool

(orcid)

Look up an author directly by ORCID (raw or URL format).

retrieve_author_works_tool

(author_id, limit=15)

Chronologically sorted publications for a given OpenAlex author.

get_author_profile_scopus_tool

(author_id)

Fetch precise Scopus-sourced h-index, citation counts, and affiliation.

get_author_profile_s2_tool

(author_id)

Fetch Semantic Scholar author profile (H-index, paper count, citations).

Citation Tracking

Tool

Signature

Description

get_citations_tool

(paper_id, direction="references")

Retrieve forward citations or backward references via OpenAlex.

Full-Text & PDF

Tool

Signature

Description

get_full_text_tool

(url, start_page=None, end_page=None)

Extract text from an OA PDF or HTML page. Supports page range selection.

get_full_text_visual_tool

(url, max_pages=3)

Render PDF pages as images for Vision-capable LLMs.

fetch_pdf_text_unpaywall_tool

(doi)

All-in-one: resolve DOI via Unpaywall → download PDF → extract text.

get_scihub_link_tool

(doi)

Attempts to resolve a strict paywalled DOI to a free direct PDF link using Sci-Hub.

fetch_pdf_text_scihub_tool

(doi)

All-in-one bypass: resolve DOI via Sci-Hub → download PDF → extract text.

Citation & Writing

Tool

Signature

Description

get_bibtex_tool

(doi)

Generate a BibTeX entry for LaTeX via CrossRef content negotiation.

format_citation_tool

(doi, style="apa")

Format citation in APA, IEEE, Chicago, Harvard, Vancouver, MLA, or Turabian.

Open Access Resolution

Tool

Signature

Description

get_unpaywall_link_tool

(doi)

Resolve a DOI to all available OA locations via Unpaywall.

Topic Mapping & Batch Analysis

Tool

Signature

Description

search_topics_tool

(query, limit=10)

Browse research topics/concepts. Returns fields, domains, and publication volume.

batch_lookup_tool

(dois: list[str])

Batch-fetch metadata for multiple DOIs in a single call (max 50).

Technical Design & Reliability

Scholar MCP is engineered for precision and fault tolerance in high-stakes research environments, utilizing several layers of protection to ensure data integrity:

  • Strict Data Contracts (Pydantic)

    • All upstream API responses are validated against Pydantic models before being returned to the agent.

    • Ensures a predictable, type-safe interface even if upstream database schemas change.

  • Fault-Tolerant Networking (Tenacity)

    • Integrated Exponential Backoff using tenacity for transient HTTP errors (429, 5xx).

    • Configurable rate-limit awareness for Elsevier and OpenAlex "polite pool" routing.

  • Resource Safety & Concurrency

    • Context-Managed Extractors: Automatic cleanup of PDF buffers and file descriptors.

    • Isolated Concurrency: Batch operations utilize asyncio.gather with localized exception handling to prevent session-wide failures.

  • System Observability

    • Structured standard-error (stderr) logging provides execution visibility during the tool lifecycle without interfering with the MCP JSON-RPC protocol.

  • Automated Verification

    • Comprehensive test suite leveraging respx for deterministic API mocking, ensuring 100% coverage of edge cases without network externalites.

Project Structure

Scholar-MCP/
├── .github/workflows/ # GitHub Actions (CI & Releases)
├── scripts/           # Automation & Validation scripts
├── tests/             # Pytest suite (respx mocked)
├── server.py          # FastMCP tool entry point
├── api.py             # API Clients (Scopus, OpenAlex, Unpaywall, CrossRef)
├── extractor.py       # PDF/HTML Extraction & Rendering
├── models.py          # Pydantic Data Validation
├── server.json        # MCP Registry Manifest
├── pyproject.toml     # Python packaging configuration
├── requirements.txt   # Dependencies
├── VERSION            # Version tracking (v1.0.0)
├── LICENSE            # MIT License
├── README.md          # Documentation
├── .env.example       # Template for API keys
└── .gitignore         # Git exclusion rules

Troubleshooting

Symptom

Cause

Resolution

HTTP 401 from Scopus

Standard API keys lack META_ABS view access.

Set SCOPUS_INST_TOKEN or use OpenAlex as fallback.

HTTP 403 on PDF download

Publisher anti-bot protection (Cloudflare, DataDome).

Provide the PDF manually to the LLM.

Empty Unpaywall results

Paper is behind a strict paywall with no OA copies.

Request the PDF from the author via ResearchGate or institutional access.

SCOPUS_API_KEY is not set

Missing environment variable.

Ensure .env is configured or pass via MCP client env block.

Contributing

  1. Fork the repository.

  2. Create a feature branch (git checkout -b feature/my-feature).

  3. Commit your changes (git commit -m 'feat: add new capability').

  4. Push to the branch (git push origin feature/my-feature).

  5. Open a Pull Request.

Please ensure all code follows PEP 8 conventions.

License

MIT License. See LICENSE for details.


Disclaimer: Automated querying of publisher APIs must comply with the respective Terms of Service of Elsevier, OpenAlex, and Unpaywall. Do not distribute API keys. Adhere to all applicable rate limits.

mcp-name: io.github.mlintangmz2765/scholar

Available Tools

27 tools
autocomplete_authors_toolA

Rapidly autocomplete author names via OpenAlex to find the correct OpenAlex ID. Useful for disambiguation before tracking works.

Inputs: name (required), limit. Returns: result

batch_lookup_toolA

Batch-fetch metadata for multiple DOIs in a single call. Accepts a list of DOIs (up to 50). Returns title, authors, year, citation count, and OA status for each. Useful for processing reference lists or comparing multiple papers at once.

Inputs: dois (required). Returns: result

fetch_pdf_text_scihub_toolB

An all-in-one bypass that resolves a DOI via Sci-Hub and directly extracts its full text using PyMuPDF.

Inputs: doi (required). Returns: result

fetch_pdf_text_unpaywall_toolA

An all-in-one bypass. Takes a DOI, resolves its best PDF on Unpaywall, and directly downloads/extracts the text using PyMuPDF.

Inputs: doi (required). Returns: result

format_citation_toolA

Format a citation for a paper in a specific style. Supported styles: apa, ieee, chicago-author-date, harvard-cite-them-right, vancouver, modern-language-association, turabian-fullnote-bibliography. Uses CrossRef/DOI content negotiation for authoritative formatting.

Inputs: doi (required), style. Returns: result

get_author_profile_s2_toolA

Get author bibliometrics from Semantic Scholar using an S2 authorId.

Inputs: author_id (required). Returns: result

get_author_profile_scopus_toolA

Retrieve Elsevier Scopus Author Profile strictly using a Scopus Author ID (digits). Returns precise academic h-index and document metrics from Scopus.

Inputs: author_id (required). Returns: result

get_bibtex_toolA

Generate a BibTeX entry for a paper given its DOI. Uses CrossRef content negotiation to produce a properly formatted BibTeX string ready for use in LaTeX documents.

Inputs: doi (required). Returns: result

get_book_details_toolA

Get detailed metadata for a specific book. Provide the book_id (e.g., OL12345W or Google Volume ID) and the source ('openlibrary' or 'googlebooks').

Inputs: book_id (required), source. Returns: result

get_citations_toolA

Tracks lineage by retrieving a paper's citations. Provide a DOI (10.xxx) or OpenAlex ID (Wxxx). Set direction="references" to see who this paper cites. Set direction="citations" to see who cited this paper recently.

Inputs: paper_id (required), direction. Returns: result

get_full_text_toolA

Extracts full text from an Open Access PDF or HTML page given its URL. This is best used after finding an OA PDF link from search_papers_openalex. Use start_page/end_page (1-indexed) to extract only specific pages from long PDFs. Warning: This can return a very large string.

Inputs: url (required), end_page, start_page. Returns: result

get_full_text_visual_toolA

Multimodal Vision Tool. Downloads a PDF and renders the specified number of pages identically into images for the AI to 'look at'. Use this if the user asks you to analyze a graph, table, format, or layout in the paper. If the text extractor doesn't capture formatting, you can use this tool to 'see' the actual PDF! Returns a sequence of texts and images (multimodal format natively parsed). Warning: High token/vision capacity used per page. Default 3 pages.

Inputs: url (required), max_pages.

get_paper_details_s2_toolA

Get detailed metadata from Semantic Scholar, including the AI-generated TLDR. Accepts an S2 paper ID or a DOI (e.g., 10.1038/nrn3241).

Inputs: paper_id (required). Returns: result

get_paper_details_toolA

Get detailed metadata and the full abstract for a specific paper. If the paper_id looks like a Scopus ID (e.g., SCOPUS_ID:85123) or a DOI (10.xxx), it uses Scopus. Returns formatted detailed text.

Inputs: paper_id (required). Returns: result

interact_with_book_toolA

Extract text or interact with a book using its Libgen MD5 hash. action:

  • 'toc': Returns the table of contents.

  • 'search': Searches for 'keyword' and returns only pages where it is found.

  • 'pages': Extracts text strictly from 'start_page' to 'end_page'.

Inputs: md5 (required), action, keyword, end_page, +1 more. Returns: result

retrieve_author_works_toolA

Retrieve chronologically sorted publications for an OpenAlex author ID. E.g., input 'W123456789' or 'https://openalex.org/A123456789'.

Inputs: author_id (required), limit. Returns: result

search_author_by_orcid_toolA

Look up an author directly by their ORCID identifier. Accepts raw ORCID (e.g. 0000-0002-9322-3515) or full URL (https://orcid.org/0000-0002-9322-3515). Returns the full author profile including h-index, works count, and affiliations.

Inputs: orcid (required). Returns: result

search_authors_toolC

Search for deep author profiles via OpenAlex. Returns h-index, i10-index, and recent institutions.

Inputs: name (required), limit, institution. Returns: result

search_books_toolA

Search for books using either 'openlibrary' or 'googlebooks'. Returns a list of matching books with titles, authors, and year.

Inputs: query (required), limit, source. Returns: result

search_libgen_toolA

Search for books in Library Genesis (Libgen). Returns books with their 'md5' which can be used to extract the text. BEST PRACTICE: To know what a book is about before downloading, ALWAYS use 'search_books_tool' (Open Library/Google Books) FIRST to read its synopsis/description. Once you decide which book is best, use this tool to find its MD5 for text extraction.

Inputs: query (required), limit. Returns: result

search_papers_s2_toolB

Search papers using Semantic Scholar (S2). S2 provides excellent relevance sorting and AI-generated TLDRs on details. NOTE: S2 has a strict 1 request/second rate limit, so this tool may be slightly slower than OpenAlex or Scopus.

Inputs: query (required), limit. Returns: result

search_papers_toolA

Searches the Scopus library by accepting standard textual querying or advanced Scopus Boolean Syntax (e.g. TITLE-ABS-KEY(artificial intelligence) AND PUBYEAR > 2020). Returns metadata summaries. Set use_scopus=False to use OpenAlex which guarantees Open Access PDF links but might have less robust abstracts in standard search. sort_by: 'relevance' (default), 'cited_by_count' (most cited first), 'publication_year' (newest first). Only works with OpenAlex. Returns a formatted string of results.

Inputs: query (required), limit, sort_by, use_scopus. Returns: result

search_titles_unpaywall_toolB

Natively search Unpaywall's database via paper titles. Set is_oa=True to strictly return Open Access results.

Inputs: query (required), is_oa. Returns: result

search_topics_toolA

Browse and discover research topics/concepts for a given keyword. Returns topic names, their parent fields, domains, and publication volume. Useful for mapping a research landscape, finding subfields, or identifying trending areas.

Inputs: query (required), limit. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 27 tools

    Disambiguation4/5

    Most tools have distinct purposes, but there are multiple tools for similar operations (e.g., author search from different sources, full-text extraction methods) which could cause confusion. Descriptions help differentiate, but an agent might struggle to choose the optimal tool without deep understanding.

    Naming Consistency3/5

    Tool names are descriptive but lack a consistent pattern. Verbs like 'search', 'get', 'fetch', 'retrieve', 'autocomplete' are used interchangeably, and some names include suffixes like '_s2', '_scopus', '_unpaywall' without a uniform convention. This can hinder predictability.

    Tool Count4/5

    27 tools is slightly above the typical range but justified by the broad domain coverage (author profiles, paper search, full text, citations, books). The tools are specialized but mostly warranted; however, some could be consolidated (e.g., multiple PDF extraction tools).

    Completeness4/5

    The server covers a comprehensive set of academic research workflows: author disambiguation, paper search across multiple sources, metadata retrieval, full-text extraction, citation analysis, and book search/interaction. Minor gaps exist, such as lack of personal collection management or advanced analytics, but core needs are well-addressed.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers