paper-mcp

Search academic papers. Returns normalized hits with a short abstract preview; call get_paper for the full record.

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    },
    "source": {
      "default": "arxiv",
      "title": "Source",
      "type": "string"
    },
    "max_results": {
      "default": 10,
      "title": "Max Results",
      "type": "integer"
    },
    "start": {
      "default": 0,
      "title": "Start",
      "type": "integer"
    },
    "sort_by": {
      "default": "relevance",
      "title": "Sort By",
      "type": "string"
    }
  },
  "required": [
    "query"
  ],
  "title": "search_papersArguments"
}

Aggregated search across arXiv, Semantic Scholar and OpenAlex 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.

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    },
    "max_results": {
      "default": 10,
      "title": "Max Results",
      "type": "integer"
    },
    "sources": {
      "default": "arxiv,semanticscholar,openalex",
      "title": "Sources",
      "type": "string"
    },
    "per_source": {
      "default": 0,
      "title": "Per Source",
      "type": "integer"
    }
  },
  "required": [
    "query"
  ],
  "title": "search_allArguments"
}

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.

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    },
    "study_types": {
      "default": "rct,meta-analysis,systematic-review",
      "title": "Study Types",
      "type": "string"
    },
    "year_from": {
      "default": 0,
      "title": "Year From",
      "type": "integer"
    },
    "max_results": {
      "default": 10,
      "title": "Max Results",
      "type": "integer"
    },
    "fetch_fulltext": {
      "default": true,
      "title": "Fetch Fulltext",
      "type": "boolean"
    }
  },
  "required": [
    "query"
  ],
  "title": "search_medicalArguments"
}

Fetch one paper by id, with full abstract and PDF link.

{
  "type": "object",
  "properties": {
    "paper_id": {
      "title": "Paper Id",
      "type": "string"
    },
    "source": {
      "default": "arxiv",
      "title": "Source",
      "type": "string"
    }
  },
  "required": [
    "paper_id"
  ],
  "title": "get_paperArguments"
}

Find papers by a specific author, newest first.

{
  "type": "object",
  "properties": {
    "author": {
      "title": "Author",
      "type": "string"
    },
    "source": {
      "default": "arxiv",
      "title": "Source",
      "type": "string"
    },
    "max_results": {
      "default": 10,
      "title": "Max Results",
      "type": "integer"
    },
    "start": {
      "default": 0,
      "title": "Start",
      "type": "integer"
    }
  },
  "required": [
    "author"
  ],
  "title": "search_by_authorArguments"
}

List the latest papers in a subject category, newest first.

{
  "type": "object",
  "properties": {
    "category": {
      "title": "Category",
      "type": "string"
    },
    "source": {
      "default": "arxiv",
      "title": "Source",
      "type": "string"
    },
    "max_results": {
      "default": 10,
      "title": "Max Results",
      "type": "integer"
    },
    "start": {
      "default": 0,
      "title": "Start",
      "type": "integer"
    }
  },
  "required": [
    "category"
  ],
  "title": "list_recentArguments"
}

List common subject category codes for filtering/recent.

{
  "type": "object",
  "properties": {
    "source": {
      "default": "arxiv",
      "title": "Source",
      "type": "string"
    }
  },
  "title": "list_categoriesArguments"
}

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.

{
  "type": "object",
  "properties": {
    "paper_id": {
      "title": "Paper Id",
      "type": "string"
    },
    "format": {
      "default": "markdown",
      "title": "Format",
      "type": "string"
    },
    "source": {
      "default": "arxiv",
      "title": "Source",
      "type": "string"
    }
  },
  "required": [
    "paper_id"
  ],
  "title": "read_paperArguments"
}

List available paper corpora.

{
  "type": "object",
  "properties": {},
  "title": "list_paper_sourcesArguments"
}

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}.

{
  "type": "object",
  "properties": {
    "image_url": {
      "default": "",
      "title": "Image Url",
      "type": "string"
    },
    "image_base64": {
      "default": "",
      "title": "Image Base64",
      "type": "string"
    },
    "model": {
      "default": "deepseek-ocr",
      "title": "Model",
      "type": "string"
    }
  },
  "title": "recognize_formulaArguments"
}

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}.

{
  "type": "object",
  "properties": {
    "image_url": {
      "default": "",
      "title": "Image Url",
      "type": "string"
    },
    "image_base64": {
      "default": "",
      "title": "Image Base64",
      "type": "string"
    },
    "model": {
      "default": "deepseek-ocr",
      "title": "Model",
      "type": "string"
    }
  },
  "title": "recognize_tableArguments"
}

List the OCR models available for recognize_formula / recognize_table.

{
  "type": "object",
  "properties": {},
  "title": "list_ocr_modelsArguments"
}

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}.

{
  "type": "object",
  "properties": {
    "code": {
      "title": "Code",
      "type": "string"
    }
  },
  "required": [
    "code"
  ],
  "title": "lint_latexArguments"
}

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.

{
  "type": "object",
  "properties": {
    "pdf_url": {
      "default": "",
      "title": "Pdf Url",
      "type": "string"
    },
    "pdf_base64": {
      "default": "",
      "title": "Pdf Base64",
      "type": "string"
    },
    "formula": {
      "default": true,
      "title": "Formula",
      "type": "boolean"
    },
    "table": {
      "default": true,
      "title": "Table",
      "type": "boolean"
    }
  },
  "title": "extract_pdfArguments"
}

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.

{
  "type": "object",
  "properties": {
    "task_id": {
      "title": "Task Id",
      "type": "string"
    }
  },
  "required": [
    "task_id"
  ],
  "title": "extract_pdf_resultArguments"
}

Semantic Scholar: papers that CITE this one (forward citation graph). id accepts S2 id / DOI: / ARXIV: / CorpusId:.

{
  "type": "object",
  "properties": {
    "paper_id": {
      "title": "Paper Id",
      "type": "string"
    },
    "max_results": {
      "default": 10,
      "title": "Max Results",
      "type": "integer"
    },
    "start": {
      "default": 0,
      "title": "Start",
      "type": "integer"
    }
  },
  "required": [
    "paper_id"
  ],
  "title": "get_paper_citationsArguments"
}

Semantic Scholar: papers this one REFERENCES (its bibliography). id accepts S2 id / DOI: / ARXIV: / CorpusId:.

{
  "type": "object",
  "properties": {
    "paper_id": {
      "title": "Paper Id",
      "type": "string"
    },
    "max_results": {
      "default": 10,
      "title": "Max Results",
      "type": "integer"
    },
    "start": {
      "default": 0,
      "title": "Start",
      "type": "integer"
    }
  },
  "required": [
    "paper_id"
  ],
  "title": "get_paper_referencesArguments"
}

Semantic Scholar: the authors of a paper (with h-index, paper/citation counts).

{
  "type": "object",
  "properties": {
    "paper_id": {
      "title": "Paper Id",
      "type": "string"
    },
    "max_results": {
      "default": 100,
      "title": "Max Results",
      "type": "integer"
    },
    "start": {
      "default": 0,
      "title": "Start",
      "type": "integer"
    }
  },
  "required": [
    "paper_id"
  ],
  "title": "get_paper_authorsArguments"
}

Semantic Scholar: find the single paper whose title best matches the given text (exact-match lookup).

{
  "type": "object",
  "properties": {
    "title": {
      "title": "Title",
      "type": "string"
    }
  },
  "required": [
    "title"
  ],
  "title": "match_paper_titleArguments"
}

Semantic Scholar: autocomplete paper titles for a partial query (fast type-ahead).

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    }
  },
  "required": [
    "query"
  ],
  "title": "autocomplete_papersArguments"
}

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.

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    },
    "sort": {
      "default": "",
      "title": "Sort",
      "type": "string"
    },
    "fields_of_study": {
      "default": "",
      "title": "Fields Of Study",
      "type": "string"
    },
    "year": {
      "default": "",
      "title": "Year",
      "type": "string"
    },
    "venue": {
      "default": "",
      "title": "Venue",
      "type": "string"
    },
    "publication_types": {
      "default": "",
      "title": "Publication Types",
      "type": "string"
    },
    "open_access_pdf": {
      "default": false,
      "title": "Open Access Pdf",
      "type": "boolean"
    },
    "token": {
      "default": "",
      "title": "Token",
      "type": "string"
    },
    "max_results": {
      "default": 100,
      "title": "Max Results",
      "type": "integer"
    }
  },
  "required": [
    "query"
  ],
  "title": "search_papers_bulkArguments"
}

Semantic Scholar: fetch many papers at once by id (S2/DOI:/ARXIV:/CorpusId:), up to ~500 per call.

{
  "type": "object",
  "properties": {
    "ids": {
      "items": {
        "type": "string"
      },
      "title": "Ids",
      "type": "array"
    }
  },
  "required": [
    "ids"
  ],
  "title": "get_papers_batchArguments"
}

Semantic Scholar: search for authors by name; returns profiles with h-index and paper/citation counts.

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    },
    "max_results": {
      "default": 10,
      "title": "Max Results",
      "type": "integer"
    },
    "start": {
      "default": 0,
      "title": "Start",
      "type": "integer"
    }
  },
  "required": [
    "query"
  ],
  "title": "search_authorsArguments"
}

Semantic Scholar: a single author's profile by id.

{
  "type": "object",
  "properties": {
    "author_id": {
      "title": "Author Id",
      "type": "string"
    }
  },
  "required": [
    "author_id"
  ],
  "title": "get_authorArguments"
}

Semantic Scholar: all papers by a given author id, newest first.

{
  "type": "object",
  "properties": {
    "author_id": {
      "title": "Author Id",
      "type": "string"
    },
    "max_results": {
      "default": 20,
      "title": "Max Results",
      "type": "integer"
    },
    "start": {
      "default": 0,
      "title": "Start",
      "type": "integer"
    }
  },
  "required": [
    "author_id"
  ],
  "title": "get_author_papersArguments"
}

Semantic Scholar: fetch many authors at once by id.

{
  "type": "object",
  "properties": {
    "ids": {
      "items": {
        "type": "string"
      },
      "title": "Ids",
      "type": "array"
    }
  },
  "required": [
    "ids"
  ],
  "title": "get_authors_batchArguments"
}

Semantic Scholar: search INSIDE paper full text and return matching text snippets (not just titles/abstracts).

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    },
    "max_results": {
      "default": 10,
      "title": "Max Results",
      "type": "integer"
    }
  },
  "required": [
    "query"
  ],
  "title": "search_snippetsArguments"
}

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.

{
  "type": "object",
  "properties": {
    "paper_id": {
      "title": "Paper Id",
      "type": "string"
    },
    "max_results": {
      "default": 10,
      "title": "Max Results",
      "type": "integer"
    },
    "pool": {
      "default": "recent",
      "title": "Pool",
      "type": "string"
    }
  },
  "required": [
    "paper_id"
  ],
  "title": "recommend_papers_for_paperArguments"
}

Semantic Scholar: recommend papers from positive (and optional negative) example paper ids.

{
  "type": "object",
  "properties": {
    "positive_ids": {
      "items": {
        "type": "string"
      },
      "title": "Positive Ids",
      "type": "array"
    },
    "negative_ids": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Negative Ids"
    },
    "max_results": {
      "default": 10,
      "title": "Max Results",
      "type": "integer"
    }
  },
  "required": [
    "positive_ids"
  ],
  "title": "recommend_papers_from_examplesArguments"
}

Semantic Scholar Datasets: list all available release ids (dated snapshots of the full corpus).

{
  "type": "object",
  "properties": {},
  "title": "list_dataset_releasesArguments"
}

Semantic Scholar Datasets: which datasets a release contains (papers, abstracts, citations, embeddings, s2orc, tldrs…). release_id defaults to 'latest'.

{
  "type": "object",
  "properties": {
    "release_id": {
      "default": "latest",
      "title": "Release Id",
      "type": "string"
    }
  },
  "title": "get_dataset_releaseArguments"
}

Semantic Scholar Datasets: get download links (presigned URLs) for one dataset in a release. Needs the API key.

{
  "type": "object",
  "properties": {
    "dataset_name": {
      "title": "Dataset Name",
      "type": "string"
    },
    "release_id": {
      "default": "latest",
      "title": "Release Id",
      "type": "string"
    }
  },
  "required": [
    "dataset_name"
  ],
  "title": "get_dataset_download_linksArguments"
}

Semantic Scholar Datasets: incremental diff (added/updated/deleted) for a dataset between two releases. Needs the key.

{
  "type": "object",
  "properties": {
    "dataset_name": {
      "title": "Dataset Name",
      "type": "string"
    },
    "start_release": {
      "title": "Start Release",
      "type": "string"
    },
    "end_release": {
      "default": "latest",
      "title": "End Release",
      "type": "string"
    }
  },
  "required": [
    "dataset_name",
    "start_release"
  ],
  "title": "get_dataset_diffsArguments"
}

OpenAlex: fetch one work's full record (316M-work, all-field corpus). id accepts OpenAlex Wxxxx, a DOI, or an arXiv id.

{
  "type": "object",
  "properties": {
    "work_id": {
      "title": "Work Id",
      "type": "string"
    }
  },
  "required": [
    "work_id"
  ],
  "title": "get_openalex_workArguments"
}

OpenAlex: papers that CITE this work (forward citation graph), most-cited first.

{
  "type": "object",
  "properties": {
    "work_id": {
      "title": "Work Id",
      "type": "string"
    },
    "max_results": {
      "default": 10,
      "title": "Max Results",
      "type": "integer"
    },
    "start": {
      "default": 0,
      "title": "Start",
      "type": "integer"
    }
  },
  "required": [
    "work_id"
  ],
  "title": "get_openalex_citationsArguments"
}

OpenAlex: the works this one REFERENCES (its bibliography).

{
  "type": "object",
  "properties": {
    "work_id": {
      "title": "Work Id",
      "type": "string"
    },
    "max_results": {
      "default": 25,
      "title": "Max Results",
      "type": "integer"
    }
  },
  "required": [
    "work_id"
  ],
  "title": "get_openalex_referencesArguments"
}

OpenAlex: search authors; returns profiles with h-index, i10-index, works/citation counts and institutions.

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    },
    "max_results": {
      "default": 10,
      "title": "Max Results",
      "type": "integer"
    },
    "start": {
      "default": 0,
      "title": "Start",
      "type": "integer"
    }
  },
  "required": [
    "query"
  ],
  "title": "search_openalex_authorsArguments"
}

OpenAlex: search institutions (universities, labs) with ROR id, country, works/citation counts.

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    },
    "max_results": {
      "default": 10,
      "title": "Max Results",
      "type": "integer"
    }
  },
  "required": [
    "query"
  ],
  "title": "search_openalex_institutionsArguments"
}

OpenAlex: advanced filtered work search. Filters: from_year, to_year, is_oa (open access only), min_citations, institution_id. sort_by: relevance|newest|cited.

{
  "type": "object",
  "properties": {
    "query": {
      "default": "",
      "title": "Query",
      "type": "string"
    },
    "from_year": {
      "default": 0,
      "title": "From Year",
      "type": "integer"
    },
    "to_year": {
      "default": 0,
      "title": "To Year",
      "type": "integer"
    },
    "is_oa": {
      "default": false,
      "title": "Is Oa",
      "type": "boolean"
    },
    "min_citations": {
      "default": 0,
      "title": "Min Citations",
      "type": "integer"
    },
    "institution_id": {
      "default": "",
      "title": "Institution Id",
      "type": "string"
    },
    "sort_by": {
      "default": "relevance",
      "title": "Sort By",
      "type": "string"
    },
    "max_results": {
      "default": 25,
      "title": "Max Results",
      "type": "integer"
    }
  },
  "title": "search_openalex_worksArguments"
}

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).

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    },
    "group_by": {
      "default": "publication_year",
      "title": "Group By",
      "type": "string"
    }
  },
  "required": [
    "query"
  ],
  "title": "get_openalex_trendsArguments"
}

OpenAlex: search the topic taxonomy (~4500 topics) to find the right subject term for filtering or recent-work queries.

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    },
    "max_results": {
      "default": 15,
      "title": "Max Results",
      "type": "integer"
    }
  },
  "required": [
    "query"
  ],
  "title": "list_openalex_topicsArguments"
}