Scholar MCP

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/liyux3-scholar-mcp

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools

6 read · 1 write · 2 delete

Secrets

9 (API keys, tokens or passwords)

Install scripts

None found

Runs as

Python package

Tools (9)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• build_paper_graphBuild a citation graphread-only

  Map a research thread by following citations from a set of seed papers. Returns nodes, edges, PageRank, bridge papers and a Mermaid diagram. Each extra hop follows another layer of citations or references. Args: paper_ids: Comma-separated DOI, arXiv, OpenAlex, S2, or exact-title seeds. max_hops: Citation/reference depth, 1-3. max_papers: Maximum graph nodes, 5-100. direction: "citations", "references", or "both". min_citations: Optional citation floor for expanded nodes. topic_filter: Optional topic phrase used to control graph drift.

• download_paperDownload a paper PDF

  Keep a paper's PDF in your local research library. Resolves an accessible copy across archives and repositories. Use read_paper for temporary reading without keeping a PDF. A successful download may replace the file at the returned path. Args: paper_id: Paper identifier (S2 ID, DOI, ArXiv:ID, etc.) save_dir: Directory to save PDF (default: configured download directory) collection: Knowledge-base collection to index the PDF in. Empty disables indexing.

• knowledge_baseManage a local paper collection (legacy)can change or delete data

  Compatibility alias for the earlier knowledge_base tool name.

• paper_infoInspect a paper and its citation neighborhoodread-only

  Look up a paper and trace what it builds on or what followed it. Citations are papers that cite it; references are papers it cites. Each relation list is ordered by citation count and limited separately. Args: paper_id: Paper identifier (S2 ID, DOI, ArXiv:ID, OpenAlex W-ID, etc.) include: Comma-separated: "detail", "citations", "references" (default: "detail") limit: Max citations/references to return (default 20)

• paper_libraryManage a local paper librarycan change or delete data

  Carry research across sessions with saved papers, collections and notes. Search queries your saved papers. save/update/remove change persistent records; remove permanently deletes matching entries. export writes an Obsidian-compatible Markdown vault. Use download_paper to save a PDF. Args: action: save/add, get, list, search, update, remove, collections, or export ("export" writes an Obsidian-compatible markdown vault) paper_ids: Comma-separated stable identifiers for save/get/update/remove paper_titles: Exact-title compatibility fallback for save collection: Collecti…

• read_paperRead a paper's main text or a page rangeread-only

  Read a paper's text, inspect figures and tables, or jump to its appendix. Returns page-aware Markdown from pages 1-10 by default, with selectors for figures and tables. Use visual to inspect a selected item. The temporary PDF is cleaned up; use download_paper to keep a local copy. Args: paper_id: Paper identifier (S2 ID, DOI, ArXiv:ID, etc.) pages: One-indexed page range. The default usually reaches the conclusion of an AI conference paper. Use ranges such as "11-20" for appendices. At most 20 pages can be read per call. visual: Optional selector returned by this …

• recommend_papersRecommend related papersread-only

  Explore related work around a paper, including connections across topics. similar finds semantic neighbours and is the default. peers finds papers cited alongside it. kin finds papers sharing its references, including connections across topics. For direct citation lists, use paper_info. Args: paper_id: Paper identifier (S2 ID, DOI, ArXiv:ID, OpenAlex ID, etc.) relation: similar | peers | kin limit: Maximum results (default 10)

• search_authorsSearch academic authorsread-only

  Find researchers and their profiles, affiliations and publication metrics. Compare returned affiliations to distinguish people with the same name. Args: query: Author name to search for limit: Maximum results (1-1000, default 5)

• search_papersSearch academic papersread-only

  Discover papers that answer a research question or match a remembered idea. Searches multiple sources, merges duplicates, follows citation connections, and ranks for relevance. Natural-language queries work without extra parameters. Use paper_info when you already have a paper identifier. For cross-language discovery, formulate the query in the language of the target literature, usually English for computer science and AI research. Args: query: Describe what you want to find. Titles, distinctive phrases, and natural-language questions all work. limit: Maximum results to retur…

Signals

Stars

5

Forks

1

Open issues

2

Weekly downloads

145

Last commit

Oct 8, 2026 (21 days ago)

Last release

Oct 7, 2026 (22 days ago)

Last package publish

Oct 7, 2026 (22 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.Liyux3/scholar-mcp

Version

0.8.5

Auth

API key

Packages

pypi scholar-mcp

License

Apache-2.0

Repository

github.com/Liyux3/scholar-mcp

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql