paper-mcp
Server Details
Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- MCPServings/paper-mcp
- GitHub Stars
- 1
- Server Listing
- paper-mcp
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 41 tools
There are several overlapping search entry points (search_all, search_papers, search_openalex_works, search_papers_bulk, search_snippets, search_medical) and parallel citation tools for Semantic Scholar vs OpenAlex. Descriptions do clarify source and intent, but an agent still needs to reason carefully about which provider-specific variant to use for common tasks like search or citation lookup.
Most names follow a predictable snake_case verb_noun pattern such as get_paper, search_authors, extract_pdf_result, and recognize_formula. Minor exceptions like search_all and list_recent are slightly less noun-specific but remain understandable and consistent with the overall convention.
With 41 tools, the surface is heavy and spans multiple providers, OCR, LaTeX linting, datasets, recommendations, and full-text extraction. Many tools are useful, but the count creates substantial cognitive load and some functional redundancy across search and citation operations.
The server covers search, metadata retrieval, authors, citation graphs, recommendations, full-text reading, PDF extraction, OCR, LaTeX linting, and dataset access across several scholarly sources. Gaps are minor, such as citation export/BibTeX support or richer institution-record lookup, but core research workflows are well covered.
Available Tools
41 toolsautocomplete_papersAInspect
Semantic Scholar: autocomplete paper titles for a partial query (fast type-ahead).
Inputs: query (required).
extract_pdfAInspect
Extract a PDF to clean Markdown/LaTeX text via MinerU (great for papers behind no open-access full text — give the user's PDF and get readable text back). Provide pdf_url (downloaded server-side, SSRF-guarded) OR pdf_base64. formula/table toggle math/table reconstruction. Returns {task_id, status, cached, content, chars}: a recently-seen (cached) or small PDF comes back with content in one call; a fresh PDF (MinerU is GPU-heavy, minutes) returns status='running' + a task_id — then call extract_pdf_result(task_id) to fetch the text.
Inputs: table, formula, pdf_url, pdf_base64.
extract_pdf_resultAInspect
Fetch the result of an extract_pdf job by task_id. Returns {task_id, status, content, chars}: content is the extracted text once status='done'; while still 'running' content is null — call again shortly. Results expire server-side, so fetch reasonably soon.
Inputs: task_id (required).
get_authorCInspect
Semantic Scholar: a single author's profile by id.
Inputs: author_id (required).
get_author_papersCInspect
Semantic Scholar: all papers by a given author id, newest first.
Inputs: author_id (required), start, max_results.
get_authors_batchCInspect
Semantic Scholar: fetch many authors at once by id.
Inputs: ids (required).
get_dataset_diffsBInspect
Semantic Scholar Datasets: incremental diff (added/updated/deleted) for a dataset between two releases. Needs the key.
Inputs: dataset_name (required), start_release (required), end_release.
get_dataset_download_linksBInspect
Semantic Scholar Datasets: get download links (presigned URLs) for one dataset in a release. Needs the API key.
Inputs: dataset_name (required), release_id.
get_dataset_releaseBInspect
Semantic Scholar Datasets: which datasets a release contains (papers, abstracts, citations, embeddings, s2orc, tldrs…). release_id defaults to 'latest'.
Inputs: release_id.
get_openalex_citationsBInspect
OpenAlex: papers that CITE this work (forward citation graph), most-cited first.
Inputs: work_id (required), start, max_results.
get_openalex_referencesCInspect
OpenAlex: the works this one REFERENCES (its bibliography).
Inputs: work_id (required), max_results.
get_openalex_trendsBInspect
OpenAlex: publication-trend analytics for a query — counts grouped by year (default), or by 'institutions.id', 'authorships.author.id', 'open_access.is_oa', 'type', 'language'. Returns aggregate counts only (cheap, no rows).
Inputs: query (required), group_by.
get_openalex_workAInspect
OpenAlex: fetch one work's full record (316M-work, all-field corpus). id accepts OpenAlex Wxxxx, a DOI, or an arXiv id.
Inputs: work_id (required).
get_paperBInspect
Fetch one paper by id, with full abstract and PDF link.
Inputs: paper_id (required), source.
get_paper_authorsCInspect
Semantic Scholar: the authors of a paper (with h-index, paper/citation counts).
Inputs: paper_id (required), start, max_results.
get_paper_citationsAInspect
Semantic Scholar: papers that CITE this one (forward citation graph). id accepts S2 id / DOI: / ARXIV: / CorpusId:.
Inputs: paper_id (required), start, max_results.
get_paper_referencesAInspect
Semantic Scholar: papers this one REFERENCES (its bibliography). id accepts S2 id / DOI: / ARXIV: / CorpusId:.
Inputs: paper_id (required), start, max_results.
get_papers_batchAInspect
Semantic Scholar: fetch many papers at once by id (S2/DOI:/ARXIV:/CorpusId:), up to ~500 per call.
Inputs: ids (required).
lint_latexAInspect
Lint a LaTeX snippet: report errors and return an auto-fixed version. Input code (the LaTeX source). Returns {errors, fixed_code, summary_en, summary_zh, elapsed_ms}.
Inputs: code (required).
list_categoriesCInspect
List common subject category codes for filtering/recent.
Inputs: source.
list_dataset_releasesAInspect
Semantic Scholar Datasets: list all available release ids (dated snapshots of the full corpus).
Inputs: no named parameters.
list_ocr_modelsAInspect
List the OCR models available for recognize_formula / recognize_table.
Inputs: no named parameters.
list_openalex_topicsBInspect
OpenAlex: search the topic taxonomy (~4500 topics) to find the right subject term for filtering or recent-work queries.
Inputs: query (required), max_results.
list_paper_sourcesBInspect
List available paper corpora.
Inputs: no named parameters.
list_recentCInspect
List the latest papers in a subject category, newest first.
Inputs: category (required), start, source, max_results.
match_paper_titleCInspect
Semantic Scholar: find the single paper whose title best matches the given text (exact-match lookup).
Inputs: title (required).
read_paperBInspect
Read a paper's full text. format='markdown' (default, body with formulas as $LaTeX$), 'html' (raw LaTeXML HTML), or 'latex' (the original LaTeX manuscript from the e-print source). arXiv only; id like 2401.01234.
Inputs: paper_id (required), format, source.
recognize_formulaAInspect
Recognize a math formula from an image and return LaTeX. Provide image_url (downloaded server-side) OR image_base64. model: deepseek-ocr (default), paddleocr-vl, or texify. Returns {latex, model, elapsed_ms}.
Inputs: model, image_url, image_base64.
recognize_tableAInspect
Recognize a table from an image and return LaTeX tabular code. Provide image_url OR image_base64. model: deepseek-ocr (default), paddleocr-vl, or texify. Returns {latex, model, elapsed_ms}.
Inputs: model, image_url, image_base64.
recommend_papers_for_paperAInspect
Semantic Scholar: recommend papers similar to one paper. pool='recent' (last open corpus) or 'all-cs' (all of CS). If the 'recent' pool yields nothing (common for older papers), it automatically retries the 'all-cs' pool.
Inputs: paper_id (required), pool, max_results.
recommend_papers_from_examplesCInspect
Semantic Scholar: recommend papers from positive (and optional negative) example paper ids.
Inputs: positive_ids (required), max_results, negative_ids.
search_allAInspect
Aggregated search across arXiv, Semantic Scholar, OpenAlex and Yongleji at once. Fans out concurrently, de-duplicates the same work across corpora (by DOI or title) and re-ranks with Reciprocal Rank Fusion, so papers found by several sources rank highest. Each hit lists which sources found it and an ids map ({source: id}) you can pass to get_paper / read_paper / the citation tools. Prefer this over search_papers for a broad lookup.
Inputs: query (required), sources, per_source, max_results.
search_authorsBInspect
Semantic Scholar: search for authors by name; returns profiles with h-index and paper/citation counts.
Inputs: query (required), start, max_results.
search_by_authorCInspect
Find papers by a specific author, newest first.
Inputs: author (required), start, source, max_results.
search_medicalAInspect
Evidence-graded MEDICAL literature search (PubMed + Europe PMC). Unlike search_all (generic, ranks high-cited reviews/guidelines above trials), this filters by research type via PubMed Publication-Type tags and re-ranks by the evidence pyramid (meta-analysis / systematic review > RCT > cohort > ...), so the actual clinical trials surface first. Open-access full text is pulled from Europe PMC by PMID. query should be English keyword/boolean text (PubMed maps it); do natural-language/multilingual understanding upstream. Returns hits with pmid/doi/study_type/evidence_level/citations/abstract and, when open-access, fulltext.
Inputs: query (required), year_from, max_results, study_types, +1 more.
search_openalex_authorsBInspect
OpenAlex: search authors; returns profiles with h-index, i10-index, works/citation counts and institutions.
Inputs: query (required), start, max_results.
search_openalex_institutionsCInspect
OpenAlex: search institutions (universities, labs) with ROR id, country, works/citation counts.
Inputs: query (required), max_results.
search_openalex_worksCInspect
OpenAlex: advanced filtered work search. Filters: from_year, to_year, is_oa (open access only), min_citations, institution_id. sort_by: relevance|newest|cited.
Inputs: is_oa, query, sort_by, to_year, +4 more.
search_papersBInspect
Search academic papers. Returns normalized hits with a short abstract preview; call get_paper for the full record.
Inputs: query (required), start, source, sort_by, +1 more.
search_papers_bulkAInspect
Semantic Scholar: bulk paper search (up to 1000 hits, sortable e.g. 'citationCount:desc' or 'publicationDate:desc', with a continuation token). Filters: fields_of_study, year (e.g. '2020-2024'), venue, publication_types, open_access_pdf.
Inputs: query (required), sort, year, token, +5 more.
search_snippetsBInspect
Semantic Scholar: search INSIDE paper full text and return matching text snippets (not just titles/abstracts).
Inputs: query (required), max_results.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Search and download academic papers from arXiv, PubMed, bioRxiv, medRxiv, Google Scholar, Semantic…
Federated search of books and papers, BibTeX/RIS citations, open-access retrieval and reading.
Academic literature search, retrieval, and private library management on top of OpenAlex.
arXiv and OpenAlex/Crossref paper search (an open Google Scholar alternative) as agent tools.
Related MCP Servers
- AlicenseAqualityCmaintenanceProvides local academic literature search and writing support by querying OpenAlex, arXiv, and Crossref, downloading open-access PDFs, extracting IMRaD sections, and appending BibTeX references.42MIT
- FlicenseNot gradedqualityDmaintenanceAggregates academic paper search from multiple databases (OpenAlex, Semantic Scholar, etc.) with PDF storage and full-text search capabilities.1-
- AlicenseBqualityBmaintenanceAI-operable research workspace integrating Zotero, Obsidian, and NotebookLM. Search papers (arXiv/Semantic Scholar/PubMed/CrossRef), ingest into Zotero, sync per-paper notes to Obsidian, verify NotebookLM briefs. All three external tools optional.76117 PyPI70MIT
- AlicenseAqualityDmaintenanceEnables searching scholarly literature across CrossRef, ERIC, Semantic Scholar, and OpenAlex, and retrieving open-access PDFs via Unpaywall.9MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.