사용 방법
- 설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
- 필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
- 입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.
npx skills add https://github.com/openags/paper-search-mcp --skill paper-search시작 전 확인
- 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
- 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.
Paper Search
Search, download, and read academic papers via the paper-search CLI.
CLI Usage
All commands run via:
paper-search <command> [args]If paper-search is not available, install it with uv tool install paper-search-mcp. Optional API keys can be configured in ~/.config/paper-search-mcp/.env.
Search
paper-search search "<query>" -n <max_per_source> -s <sources> -y <year>-n: results per source (default: 5)-s: comma-separated sources, "fast", "fastest", or "all" (default: all)--exhaustive: compatibility no-op (broad search is already the default); explicit-salways takes precedence-y: year filter for Semantic Scholar (e.g. "2020", "2018-2022")
For speed, use -s fast (OpenAlex, Crossref, arXiv, PubMed, Europe PMC; also Semantic Scholar when its API key is nonblank) or -s fastest (OpenAlex and Crossref). Explicit source choices are never expanded, even for DOI queries. Use -s unpaywall for DOI lookup; "all" already includes it. These presets do not enable optional paid sources.
Download PDF
paper-search download <source> <paper_id> [-o ./downloads]Read (extract text)
paper-search read <source> <paper_id> [-o ./downloads]List sources
paper-search sourcesMCP tools from the CLI
paper-search tool calls the same registered tools as the MCP server, including source-specific options and DOI lookup. Required arguments are positional; optional arguments use kebab-case flags. Boolean flags use --flag and --no-flag; omitted options retain their MCP defaults.
paper-search tool --help
paper-search tool --list # JSON tool list, schemas, and annotations
paper-search tool search_crossref --help
paper-search tool search_crossref "transformer attention" --filter from-pub-date:2024-01-01 --sort published --order desc --max-results 2
paper-search tool get_crossref_paper_by_doi 10.1038/nature12373
paper-search tool search_iacr "cryptography" --no-fetch-detailsObjects and lists return JSON; text and download paths return plain text. An exception returns a JSON error with exit code 1; invalid CLI syntax exits with code 2. A normal MCP result retains its original meaning, including error or partial-result fields returned by the tool itself. --list shows only tools enabled by the current configuration, so IEEE tools still require their API key. The existing search, download, read, and sources commands are unchanged. Tool calls keep the MCP tools' source selection and timeout behavior; Sci-Hub fallback remains opt-in through --use-scihub.
Output
search and download return JSON. read returns plain text. Config warnings go to stderr and can be ignored.
Sources
arxiv, pubmed, biorxiv, medrxiv, google_scholar, iacr, semantic, crossref, openalex, pmc, core, europepmc, dblp, openaire, citeseerx, doaj, base, zenodo, hal, ssrn, openreview, unpaywall, acm
Optional (env vars): ieee (IEEE_API_KEY). ACM search is keyless and uses Crossref metadata; publisher PDF access may require the OA fallback.
Web of Science (wos) and Scopus (scopus) require their runtime API keys and explicit source selection; they are never added to all, fast, or fastest. Use --wos-db or the --scopus-view, --scopus-sort, --scopus-field, and --scopus-date options on ordinary search, or inspect their corresponding tool help. read scopus <id> returns structured abstract metadata; --full-text explicitly attempts identity-verified article text and returns a nonzero exit when full text remains unavailable. An abstract-only result is not full text.
The tool command also exposes get_citing_papers, get_referenced_papers, get_search_cache_status, and clear_search_cache. Relationship lookups accept DOIs/OpenAlex IDs, with bounded one-hop retrieval. Caching is off by default; enabling it persists queries and public results, and requires an explicit operator choice. Clearing the search cache does not remove downloaded PDFs.
Workflow
- Search with targeted sources to find papers
- Present results as a table: title, authors, year, source, DOI/URL
- If the user wants full text, use
read <source> <paper_id> - If the user wants the PDF, use
download <source> <paper_id>and report the saved path