academia-mcp 0.0.2__py3-none-any.whl

academia_mcp/__init__.py

@@ -0,0 +1,7 @@
+from .server import server
+
+__version__ = "0.0.1"
+
+
+def main() -> None:
+    server.run()

academia_mcp/__main__.py

@@ -0,0 +1,5 @@
+from . import main
+
+
+if __name__ == "__main__":
+    main()

academia_mcp/server.py

@@ -0,0 +1,19 @@
+from mcp.server.fastmcp import FastMCP
+
+from .tools.arxiv_search import arxiv_search
+from .tools.arxiv_download import arxiv_download
+from .tools.s2_citations import s2_citations
+from .tools.hf_datasets_search import hf_datasets_search
+from .tools.anthology_search import anthology_search
+
+server = FastMCP("Academia MCP")
+
+server.add_tool(arxiv_search)
+server.add_tool(arxiv_download)
+server.add_tool(s2_citations)
+server.add_tool(hf_datasets_search)
+server.add_tool(anthology_search)
+
+
+if __name__ == "__main__":
+    server.run()

academia_mcp/tools/__init__.py

@@ -0,0 +1,14 @@
+from .arxiv_search import arxiv_search
+from .anthology_search import anthology_search
+from .arxiv_download import arxiv_download
+from .hf_datasets_search import hf_datasets_search
+from .s2_citations import s2_citations
+
+
+__all__ = [
+    "arxiv_search",
+    "arxiv_download",
+    "anthology_search",
+    "s2_citations",
+    "hf_datasets_search",
+]

academia_mcp/tools/anthology_search.py

@@ -0,0 +1,193 @@
+import json
+import re
+from datetime import datetime
+from typing import Optional, List, Dict, Any
+
+from acl_anthology import Anthology
+
+
+class AnthologySingleton:
+    instance: Optional[Anthology] = None
+
+    @classmethod
+    def get(cls) -> Anthology:
+        if cls.instance is None:
+            cls.instance = Anthology.from_repo()
+            cls.instance.load_all()
+        return cls.instance
+
+
+SORT_BY_OPTIONS = ("relevance", "published")
+SORT_ORDER_OPTIONS = ("ascending", "descending")
+
+
+def _format_text_field(text: str) -> str:
+    return " ".join([line.strip() for line in text.split() if line.strip()])
+
+
+def _format_authors(authors: List[Any]) -> str:
+    names = [f"{author.name.first} {author.name.last}" for author in authors]
+    result = ", ".join(names[:3])
+    if len(names) > 3:
+        result += f", and {len(names) - 3} more authors"
+    return result
+
+
+def _format_date(date_str: str) -> str:
+    try:
+        return datetime.strptime(date_str, "%Y").strftime("%B %d, %Y")
+    except ValueError:
+        return date_str
+
+
+def _clean_entry(entry: Any) -> Dict[str, Any]:
+    return {
+        "id": entry.full_id,
+        "title": _format_text_field(entry.title.as_text()),
+        "authors": _format_authors(entry.authors),
+        "abstract": (_format_text_field(entry.abstract.as_text()) if entry.abstract else ""),
+        "published": _format_date(entry.year),
+        "categories": ", ".join(entry.venue_ids),
+        "comment": entry.note if entry.note else "",
+        "url": entry.pdf.url if entry.pdf else "",
+    }
+
+
+def _convert_to_year(date_str: str) -> int:
+    try:
+        return int(date_str[:4])
+    except ValueError as e:
+        raise ValueError("Invalid date format. Please use YYYY-MM-DD format.") from e
+
+
+def _has_cyrillic(text: str) -> bool:
+    return bool(re.search("[а-яА-Я]", text))
+
+
+def _parse_query(query: str, paper: Any) -> bool:
+    conditions = re.split(r"\s+(AND|OR|ANDNOT)\s+", query)
+    result = False
+    for i in range(0, len(conditions), 2):
+        condition = conditions[i]
+        field, value = condition.split(":", 1) if ":" in condition else ("ti", condition)
+        value = value.lower().replace('"', "").replace("'", "")
+        match field:
+            case "ti":
+                match_found = value in paper.title.as_text().lower()
+            case "au":
+                match_found = any(value in str(author).lower() for author in paper.authors)
+            case "abs":
+                match_found = paper.abstract and value in paper.abstract.as_text().lower()
+            case "cat":
+                match_found = any(value in cat.lower() for cat in paper.venue_ids)
+            case "id":
+                match_found = value in paper.full_id.lower()
+            case _:
+                match_found = False
+        if i == 0:
+            result = match_found
+        else:
+            operator = conditions[i - 1]
+            if operator == "AND":
+                result = result and match_found
+            elif operator == "OR":
+                result = result or match_found
+            elif operator == "ANDNOT":
+                result = result and not match_found
+    return result
+
+
+def anthology_search(
+    query: str,
+    offset: Optional[int] = 0,
+    limit: Optional[int] = 5,
+    start_date: Optional[str] = None,
+    end_date: Optional[str] = None,
+    sort_by: Optional[str] = "relevance",
+    sort_order: Optional[str] = "descending",
+    include_abstracts: Optional[bool] = False,
+) -> str:
+    """
+    Search ACL Anthology papers with field-specific queries.
+
+    Fields:
+        all: (all fields), ti: (title), au: (author),
+        abs: (abstract), cat: (category), id: (ID without version)
+
+    Operators:
+        AND, OR, ANDNOT
+
+    Please always specify the fields. Search should always be field-specific.
+    You can search for an exact match of an entire phrase by enclosing the phrase in double quotes.
+    If you do not need an exact match of a phrase, use single terms with OR/AND.
+    Boolean operators are strict. In most cases, you need OR and not AND.
+    You can scroll all search results with the "offset" parameter.
+    Do not include date constraints in the query: use "start_date" and "end_date" parameters instead.
+    The names of authors should be in Latin script. For example, search "Ilya Gusev" instead of "Илья Гусев".
+
+    Example queries:
+        abs:"machine learning"
+        au:"del maestro"
+        au:vaswani AND ti:"attention is all"
+        all:role OR all:playing OR all:"language model"
+        (au:vaswani OR au:"del maestro") ANDNOT ti:attention
+
+    Return a JSON object serialized to a string. The structure is:
+    {"total_count": ..., "returned_count": ..., "offset": ..., "results": [...]}
+    Every item in the "results" has the following fields:
+    ("index", "id", "title", "authors", "abstract", "published", "updated", "categories", "comment")
+    You can use `json.loads` to deserialize the result and get specific fields.
+
+    Args:
+        query: The search query, required.
+        offset: The offset in search results. If it is 10, the first 10 items will be skipped. 0 by default.
+        limit: The maximum number of items that will be returned. limit=5 by default, limit=10 is the maximum.
+        start_date: Start date in %Y-%m-%d format. None by default.
+        end_date: End date in %Y-%m-%d format. None by default.
+        sort_by: 3 options to sort by: relevance, lastUpdatedDate, submittedDate. relevance by default.
+        sort_order: 2 sort orders: ascending, descending. descending by default.
+        include_abstracts: include abstracts in the result or not. False by default.
+    """
+    assert isinstance(query, str), "Error: Your search query must be a string"
+    assert isinstance(offset, int), "Error: offset should be an integer"
+    assert isinstance(limit, int), "Error: limit should be an integer"
+    assert isinstance(sort_by, str), "Error: sort_by should be a string"
+    assert isinstance(sort_order, str), "Error: sort_order should be a string"
+    assert query.strip(), "Error: Your query should not be empty"
+    assert sort_by in SORT_BY_OPTIONS, f"Error: sort_by should be one of {SORT_BY_OPTIONS}"
+    assert (
+        sort_order in SORT_ORDER_OPTIONS
+    ), f"Error: sort_order should be one of {SORT_ORDER_OPTIONS}"
+    assert offset >= 0, "Error: offset must be 0 or positive number"
+    assert limit < 100, "Error: limit is too large, it should be less than 100"
+    assert limit > 0, "Error: limit should be greater than 0"
+    assert not _has_cyrillic(query), "Error: use only Latin script for queries"
+    assert include_abstracts is not None, "Error: include_abstracts must be bool"
+
+    singleton = AnthologySingleton.get()
+    all_papers = [
+        paper for paper in singleton.papers() if paper.abstract and str(paper.abstract).strip()
+    ]
+
+    if start_date or end_date:
+        start_year = _convert_to_year(start_date) if start_date else 1900
+        end_year = _convert_to_year(end_date) if end_date else datetime.now().year
+        all_papers = [paper for paper in all_papers if start_year <= int(paper.year) <= end_year]
+
+    filtered_papers = [paper for paper in all_papers if _parse_query(query, paper)]
+
+    if sort_by == "published":
+        filtered_papers.sort(key=lambda x: int(x.year), reverse=(sort_order == "descending"))
+
+    paged_papers = filtered_papers[offset : offset + limit]
+    clean_entries = [_clean_entry(entry) for entry in paged_papers]
+
+    return json.dumps(
+        {
+            "total_count": len(filtered_papers),
+            "returned_count": len(paged_papers),
+            "offset": offset,
+            "results": clean_entries,
+        },
+        ensure_ascii=False,
+    )

academia_mcp/tools/arxiv_download.py

@@ -0,0 +1,326 @@
+# Based on
+# https://github.com/SamuelSchmidgall/AgentLaboratory/blob/main/tools.py
+# https://github.com/bytedance/pasa/blob/main/utils.py
+
+import re
+import json
+import tempfile
+from pathlib import Path
+from typing import Any, List, Optional, Dict
+from dataclasses import dataclass, field
+
+import requests
+import bs4
+from markdownify import MarkdownConverter  # type: ignore
+from pypdf import PdfReader
+
+
+def download_pdf(url: str, output_path: Path) -> None:
+    response = requests.get(url)
+    response.raise_for_status()
+    content_type = response.headers.get("content-type")
+    assert content_type
+    assert "application/pdf" in content_type.lower()
+    with open(output_path.resolve(), "wb") as fp:
+        fp.write(response.content)
+
+
+def parse_pdf_file(pdf_path: Path) -> List[str]:
+    # Why not Marker? Because it is too heavy.
+    reader = PdfReader(str(pdf_path.resolve()))
+
+    pages = []
+    for page_number, page in enumerate(reader.pages, start=1):
+        try:
+            text = page.extract_text()
+            prefix = f"## Page {page_number}\n\n"
+            pages.append(prefix + text)
+        except Exception:
+            continue
+    return pages
+
+
+HTML_URL = "https://arxiv.org/html/{paper_id}"
+ABS_URL = "https://arxiv.org/abs/{paper_id}"
+PDF_URL = "https://arxiv.org/pdf/{paper_id}"
+SECTION_STOP_WORDS = (
+    "references",
+    "acknowledgments",
+    "about this document",
+    "appendix",
+)
+
+
+@dataclass
+class TOCEntry:
+    level: int
+    title: str
+    html_id: Optional[str] = None
+    subsections: List["TOCEntry"] = field(default_factory=list)
+
+    def linearize(self) -> List["TOCEntry"]:
+        entries = [self]
+        for subsection in self.subsections:
+            entries.extend(subsection.linearize())
+        return entries
+
+    def is_excluded(self) -> bool:
+        return any(ss in self.title.lower() for ss in SECTION_STOP_WORDS)
+
+    def to_str(self) -> str:
+        final_items = []
+        output_index = 0
+        for entry in self.linearize():
+            if entry.level <= 1:
+                continue
+            prefix = "  " * (entry.level - 2)
+            suffix = ""
+            if entry.level == 2 and not entry.is_excluded():
+                suffix = f" (index in 'sections': {output_index})"
+                output_index += 1
+            final_items.append(prefix + entry.title + suffix)
+        return "\n".join(final_items)
+
+
+class ArxivHTMLConverter(MarkdownConverter):  # type: ignore
+    def __init__(self, base_url: str, *args: Any, **kwargs: Any) -> None:
+        self.base_url = base_url
+
+        super().__init__(*args, **kwargs)
+
+    def convert_cite(self, el: bs4.element.Tag, text: str, convert_as_inline: bool = False) -> str:
+        citations = text.split(";")
+        citations = [c.strip() for c in citations if c.strip()]
+        fixed_citations = []
+        for citation in citations:
+            fixed_citation = citation
+            parts = citation.split()
+            year = parts[-1]
+            if len(year) > 4 and year[0] == "(" and year[-1] == ")":
+                fixed_citation = f'{" ".join(parts[:-1])}, {year[1:-1]}'
+            fixed_citations.append(fixed_citation)
+        return f'({"; ".join(fixed_citations)})'
+
+    def convert_sup(self, *args: Any, **kwargs: Any) -> str:
+        return ""
+
+    def convert_span(self, el: bs4.element.Tag, text: str, convert_as_inline: bool = False) -> str:
+        if "class" not in el:
+            return text
+        if "ltx_tag_item" in el["class"]:
+            return ""
+        if "ltx_note_outer" in el["class"]:
+            return f" (Footnote {text})"
+        if "ltx_tag_note" in el["class"]:
+            return text + ": "
+        return text
+
+    def convert_figure(
+        self, el: bs4.element.Tag, text: str, convert_as_inline: bool = False
+    ) -> str:
+        if el.img:
+            link = el.img.get("src")
+            caption = "Figure"
+            if el.figcaption:
+                caption = el.figcaption.text
+            return f"\n\n![{caption}]({self.base_url}/{link})\n\n"
+        elif el.table:
+            caption = "Table"
+            if el.figcaption:
+                caption = el.figcaption.text
+            table_text = self.process_tag(el.table, convert_as_inline=False)
+            return f"\n\n{caption}\n\n{table_text}\n\n"
+        return text
+
+
+def _generate_toc(soup: bs4.element.Tag) -> TOCEntry:
+    stack = [TOCEntry(level=0, title="ROOT", html_id=None)]
+    heading_tags = {"h1": 1, "h2": 2, "h3": 3, "h4": 4, "h5": 5}
+    for tag in soup.find_all(heading_tags.keys()):
+        level = heading_tags[tag.name]
+        while stack[-1].level >= level:
+            stack.pop()
+        parent_entry = stack[-1]
+        section = tag.find_parent("section", id=True)
+        if not section:
+            continue
+        section_id = section.get("id")
+        assert section_id is not None
+        title = tag.get_text().strip()
+        new_entry = TOCEntry(level=level, title=title, html_id=section_id)
+        parent_entry.subsections.append(new_entry)
+        stack.append(new_entry)
+    return stack[0]
+
+
+def _convert_soup_to_md(soup: bs4.element.Tag, url: str) -> str:
+    converter = ArxivHTMLConverter(base_url=url, strip=["div", "a"], heading_style="ATX")
+    md_content: str = converter.convert_soup(soup)
+    md_content = md_content.replace("\xa0", " ")
+    md_content = "\n".join([line.strip() for line in md_content.split("\n")])
+    lines = [line.strip() for line in md_content.split("\n\n") if line.strip()]
+    md_content = "\n\n".join(lines)
+    return md_content
+
+
+def _build_by_toc(toc: TOCEntry, soup: bs4.element.Tag, url: str) -> List[str]:
+    final_sections = []
+    for toc_entry in toc.linearize():
+        if toc_entry.level == 2 and not toc_entry.is_excluded():
+            section = soup.find(id=toc_entry.html_id)
+            assert isinstance(section, bs4.element.Tag)
+            text = _convert_soup_to_md(section, url)
+            final_sections.append(text)
+    return final_sections
+
+
+def _format_authors(authors: str) -> str:
+    if not authors:
+        return ""
+    names = authors.split(",")
+    names = [n.strip() for n in names if n.strip()]
+    result = ", ".join(names[:3])
+    if len(names) > 3:
+        result += f", and {len(names) - 3} more authors"
+    return result
+
+
+def _parse_citation_metadata(metas: List[str]) -> Dict[str, Any]:
+    metas = [item.replace("\n", " ") for item in metas]
+    meta_string = " ".join(metas)
+    authors, title, journal, year = "", "", "", None
+    if len(metas) == 3:
+        authors, title, journal = metas
+    else:
+        meta_string = re.sub(r"\.\s\d{4}[a-z]?\.", ".", meta_string)
+        match = re.match(r"^(.*?\.\s)(.*?)(\.\s.*|$)", meta_string, re.DOTALL)
+        if match:
+            authors = match.group(1).strip() if match.group(1) else ""
+            title = match.group(2).strip() if match.group(2) else ""
+            journal = match.group(3).strip() if match.group(3) else ""
+            if journal.startswith(". "):
+                journal = journal[2:]
+
+    if authors:
+        parts = authors.strip(".").split(".")
+        if parts and parts[-1].strip().isdigit():
+            year = int(parts[-1].strip())
+            authors = ".".join(parts[:-1])
+        authors = _format_authors(authors)
+
+    result = {
+        "authors": authors,
+        "year": year,
+        "title": title,
+        "journal": journal,
+    }
+    if not authors or not title:
+        result["meta"] = meta_string
+    return result
+
+
+def _extract_citations(soup_biblist: bs4.element.Tag) -> List[Dict[str, Any]]:
+    extracted = []
+    for li in soup_biblist.find_all("li", recursive=False):
+        metas = [x.text.strip() for x in li.find_all("span", class_="ltx_bibblock")]
+        extracted.append(_parse_citation_metadata(metas))
+    return extracted
+
+
+def _parse_html(paper_id: str) -> Dict[str, Any]:
+    url = HTML_URL.format(paper_id=paper_id)
+    response = requests.get(url)
+    response.raise_for_status()
+    content = response.text
+
+    soup = bs4.BeautifulSoup(content, features="lxml")
+    article = soup.article
+    assert article and isinstance(article, bs4.element.Tag)
+
+    citations = []
+    biblist_tag = article.find(class_="ltx_biblist")
+    if biblist_tag and isinstance(biblist_tag, bs4.element.Tag):
+        citations = _extract_citations(biblist_tag)
+
+    toc = _generate_toc(article)
+    sections = _build_by_toc(toc, article, url)
+    return {
+        "toc": toc.to_str(),
+        "sections": sections,
+        "citations": citations,
+        "original_format": "html",
+    }
+
+
+def _parse_abs(paper_id: str) -> Dict[str, str]:
+    url = ABS_URL.format(paper_id=paper_id)
+    response = requests.get(url)
+    response.raise_for_status()
+    content = response.text
+
+    soup = bs4.BeautifulSoup(content, features="lxml")
+    title_tag = soup.find(class_="title")
+    assert title_tag and isinstance(title_tag, bs4.element.Tag)
+    title = title_tag.get_text().strip()
+    title = title.replace("Title:", "")
+    abstract_tag = soup.find(class_="abstract")
+    assert abstract_tag and isinstance(abstract_tag, bs4.element.Tag)
+    abstract = abstract_tag.get_text().strip()
+    abstract = abstract.replace("Abstract:", "")
+    return {"title": title, "abstract": abstract}
+
+
+def _parse_pdf(paper_id: str) -> Dict[str, Any]:
+    url = PDF_URL.format(paper_id=paper_id)
+    with tempfile.NamedTemporaryFile(mode="w", delete=True) as temp_file:
+        download_pdf(url, Path(temp_file.name))
+        pages: List[str] = parse_pdf_file(Path(temp_file.name))
+    return {
+        "toc": "\n".join([f"Page {page_number}" for page_number in range(1, len(pages) + 1)]),
+        "sections": pages,
+        "citations": [],
+        "original_format": "pdf",
+    }
+
+
+def arxiv_download(
+    paper_id: str,
+    include_citations: Optional[bool] = False,
+    mode: Optional[str] = "html",
+) -> str:
+    """
+    Downloads a paper from Arxiv and converts it to text.
+    Use mode = "html" by default.
+    Fall back to mode = "pdf" if there are any problems with the HTML version.
+
+    Returns a JSON with a following structure:
+    {
+        "title": "...",
+        "abstract": "...",
+        "toc": "...",
+        "sections": ["...", ...],
+        "citations": [...]
+    }
+    Use `json.loads` to deserialize the result if you want to get specific fields.
+    For example, `abstract = json.loads(arxiv_download("2409.06820v1"))`
+    The "toc" key contains Table of Contents, that sometimes has indexing for sections.
+
+    Args:
+        paper_id: ID of the paper on Arxiv. For instance: 2409.06820v1
+        include_citations: include "citations" in the result or not. False by default.
+        mode: Which version of paper to use. Options: ["html", "pdf"]. "html" by default.
+    """
+
+    abs_meta = _parse_abs(paper_id)
+    if mode == "html":
+        try:
+            content = _parse_html(paper_id)
+        except requests.exceptions.HTTPError:
+            content = _parse_pdf(paper_id)
+    else:
+        content = _parse_pdf(paper_id)
+
+    if not include_citations and "citations" in content:
+        content.pop("citations")
+
+    return json.dumps({**abs_meta, **content}, ensure_ascii=False)

academia_mcp/tools/arxiv_search.py

@@ -0,0 +1,246 @@
+# Based on
+# https://github.com/jonatasgrosman/findpapers/blob/master/findpapers/searchers/arxiv_searcher.py
+# https://info.arxiv.org/help/api/user-manual.html
+
+import json
+import re
+from typing import Optional, List, Dict, Any, Union
+from datetime import datetime, date
+from urllib3.util.retry import Retry
+
+import requests
+import xmltodict
+
+BASE_URL = "http://export.arxiv.org"
+URL_TEMPLATE = "{base_url}/api/query?search_query={query}&start={start}&sortBy={sort_by}&sortOrder={sort_order}&max_results={limit}"
+SORT_BY_OPTIONS = ("relevance", "lastUpdatedDate", "submittedDate")
+SORT_ORDER_OPTIONS = ("ascending", "descending")
+
+
+def _format_text_field(text: str) -> str:
+    return " ".join([line.strip() for line in text.split() if line.strip()])
+
+
+def _format_authors(authors: Union[List[Dict[str, str]], Dict[str, str]]) -> str:
+    if not authors:
+        return ""
+    if isinstance(authors, dict):
+        authors = [authors]
+    names = [author["name"] for author in authors]
+    result = ", ".join(names[:3])
+    if len(names) > 3:
+        result += f", and {len(names) - 3} more authors"
+    return result
+
+
+def _format_categories(categories: Union[List[Dict[str, Any]], Dict[str, Any]]) -> str:
+    if not categories:
+        return ""
+    if isinstance(categories, dict):
+        categories = [categories]
+    clean_categories = [c.get("@term", "") for c in categories]
+    clean_categories = [c.strip() for c in clean_categories if c.strip()]
+    return ", ".join(clean_categories)
+
+
+def _format_date(date: str) -> str:
+    dt = datetime.strptime(date, "%Y-%m-%dT%H:%M:%SZ")
+    return dt.strftime("%B %d, %Y")
+
+
+def _clean_entry(entry: Dict[str, Any]) -> Dict[str, Any]:
+    return {
+        "id": entry["id"].split("/")[-1],
+        "title": _format_text_field(entry["title"]),
+        "authors": _format_authors(entry["author"]),
+        "abstract": _format_text_field(entry["summary"]),
+        "published": _format_date(entry["published"]),
+        "updated": _format_date(entry["updated"]),
+        "categories": _format_categories(entry.get("category", {})),
+        "comment": _format_text_field(entry.get("arxiv:comment", {}).get("#text", "")),
+    }
+
+
+def _convert_to_yyyymmddtttt(date_str: str) -> str:
+    try:
+        date_obj = datetime.strptime(date_str, "%Y-%m-%d")
+        return date_obj.strftime("%Y%m%d") + "0000"
+    except ValueError as e:
+        raise ValueError("Invalid date format. Please use YYYY-MM-DD format.") from e
+
+
+def _has_cyrillic(text: str) -> bool:
+    return bool(re.search("[а-яА-Я]", text))
+
+
+def _compose_query(
+    orig_query: str,
+    start_date: Optional[str] = None,
+    end_date: Optional[str] = None,
+) -> str:
+    query: str = orig_query.replace(" AND NOT ", " ANDNOT ")
+    if "-" in query:
+        query = f"({query}) OR ({query.replace('-', ' ')})"
+
+    if start_date or end_date:
+        if not start_date:
+            start_date = "1900-01-01"
+        if not end_date:
+            today = date.today()
+            end_date = today.strftime("%Y-%m-%d")
+        date_filter = (
+            f"[{_convert_to_yyyymmddtttt(start_date)} TO {_convert_to_yyyymmddtttt(end_date)}]"
+        )
+        query = f"({query}) AND submittedDate:{date_filter}"
+
+    query = query.replace(" ", "+")
+    query = query.replace('"', "%22")
+    query = query.replace("(", "%28")
+    query = query.replace(")", "%29")
+    return query
+
+
+def _format_entries(
+    entries: List[Dict[str, Any]],
+    start_index: int,
+    include_abstracts: bool,
+    total_results: int,
+) -> str:
+    clean_entries: List[Dict[str, Any]] = []
+    for entry_num, entry in enumerate(entries):
+        clean_entry = _clean_entry(entry)
+        if not include_abstracts:
+            clean_entry.pop("abstract")
+        clean_entry["index"] = start_index + entry_num
+        clean_entries.append(clean_entry)
+    return json.dumps(
+        {
+            "total_count": total_results,
+            "returned_count": len(entries),
+            "offset": start_index,
+            "results": clean_entries,
+        },
+        ensure_ascii=False,
+    )
+
+
+def _get_results(url: str) -> requests.Response:
+    retry_strategy = Retry(
+        total=3,
+        backoff_factor=3,
+        status_forcelist=[500, 502, 503, 504],
+        allowed_methods=["GET"],
+    )
+
+    session = requests.Session()
+    adapter = requests.adapters.HTTPAdapter(max_retries=retry_strategy)
+    session.mount("http://", adapter)
+
+    try:
+        response = session.get(url, timeout=30)
+        response.raise_for_status()
+        return response
+    except (
+        requests.exceptions.ConnectionError,
+        requests.exceptions.RequestException,
+    ) as e:
+        print(f"Failed after {retry_strategy.total} retries: {str(e)}")
+        raise
+
+    return response
+
+
+def arxiv_search(
+    query: str,
+    offset: Optional[int] = 0,
+    limit: Optional[int] = 5,
+    start_date: Optional[str] = None,
+    end_date: Optional[str] = None,
+    sort_by: Optional[str] = "relevance",
+    sort_order: Optional[str] = "descending",
+    include_abstracts: Optional[bool] = False,
+) -> str:
+    """
+    Search arXiv papers with field-specific queries.
+
+    Fields:
+        all: (all fields), ti: (title), au: (author),
+        abs: (abstract), cat: (category), id: (ID without version)
+
+    Operators:
+        AND, OR, ANDNOT
+
+    Please always specify the fields. Search should always be field-specific.
+    You can search for an exact match of an entire phrase by enclosing the phrase in double quotes.
+    If you do not need an exact match of a phrase, use single terms with OR/AND.
+    Boolean operators are strict. OR is better in most cases.
+    Do not include date constraints in the query: use "start_date" and "end_date" parameters instead.
+    Use Latin script for names. For example, search "Ilya Gusev" instead of "Илья Гусев".
+
+    Example queries:
+        all:"machine learning"
+        au:"del maestro"
+        au:vaswani AND abs:"attention is all"
+        all:role OR all:playing OR all:"language model"
+        (au:vaswani OR au:"del maestro") ANDNOT ti:attention
+
+    Returns a JSON object serialized to a string. The structure is:
+    {"total_count": ..., "returned_count": ..., "offset": ..., "results": [...]}
+    Every item in the "results" has the following fields:
+    ("index", "id", "title", "authors", "abstract", "published", "updated", "categories", "comment")
+    Use `json.loads` to deserialize the result if you want to get specific fields.
+
+    Args:
+        query: The search query, required.
+        offset: The offset to scroll search results. 10 items will be skipped if offset=10. 0 by default.
+        limit: The maximum number of items to return. limit=5 by default, limit=10 is the maximum.
+        start_date: Start date in %Y-%m-%d format. None by default.
+        end_date: End date in %Y-%m-%d format. None by default.
+        sort_by: 3 options to sort by: relevance, lastUpdatedDate, submittedDate. relevance by default.
+        sort_order: 2 sort orders: ascending, descending. descending by default.
+        include_abstracts: include abstracts in the result or not. False by default.
+    """
+
+    assert isinstance(query, str), "Error: Your search query must be a string"
+    assert isinstance(offset, int), "Error: offset should be an integer"
+    assert isinstance(limit, int), "Error: limit should be an integer"
+    assert isinstance(sort_by, str), "Error: sort_by should be a string"
+    assert isinstance(sort_order, str), "Error: sort_order should be a string"
+    assert query.strip(), "Error: Your query should not be empty"
+    assert sort_by in SORT_BY_OPTIONS, f"Error: sort_by should be one of {SORT_BY_OPTIONS}"
+    assert (
+        sort_order in SORT_ORDER_OPTIONS
+    ), f"Error: sort_order should be one of {SORT_ORDER_OPTIONS}"
+    assert offset >= 0, "Error: offset must be 0 or positive number"
+    assert limit < 100, "Error: limit is too large, it should be less than 100"
+    assert limit > 0, "Error: limit should be greater than 0"
+    assert not _has_cyrillic(query), "Error: use only Latin script for queries"
+    assert include_abstracts is not None, "Error: include_abstracts must be bool"
+
+    fixed_query: str = _compose_query(query, start_date, end_date)
+    url = URL_TEMPLATE.format(
+        base_url=BASE_URL,
+        query=fixed_query,
+        start=offset,
+        limit=limit,
+        sort_by=sort_by,
+        sort_order=sort_order,
+    )
+
+    response = _get_results(url)
+    content = response.content
+    parsed_content = xmltodict.parse(content)
+
+    feed = parsed_content.get("feed", {})
+    total_results = int(feed.get("opensearch:totalResults", {}).get("#text", 0))
+    start_index = int(feed.get("opensearch:startIndex", {}).get("#text", 0))
+    entries = feed.get("entry", [])
+    if isinstance(entries, dict):
+        entries = [entries]
+    formatted_entries: str = _format_entries(
+        entries,
+        start_index=start_index,
+        total_results=total_results,
+        include_abstracts=include_abstracts,
+    )
+    return formatted_entries

academia_mcp/tools/hf_datasets_search.py

@@ -0,0 +1,82 @@
+import json
+from datetime import datetime
+from typing import Optional, List, Dict, Any, Literal
+
+from huggingface_hub import HfApi, DatasetInfo, hf_hub_download
+
+HF_API = HfApi()
+
+
+def _format_date(dt: Optional[datetime]) -> str:
+    if not dt:
+        return ""
+    return dt.strftime("%B %d, %Y")
+
+
+def _clean_entry(entry: DatasetInfo) -> Dict[str, Any]:
+    try:
+        readme_path = hf_hub_download(repo_id=entry.id, repo_type="dataset", filename="README.md")
+        with open(readme_path, "r", encoding="utf-8") as f:
+            readme_content = f.read()
+    except Exception:
+        readme_content = ""
+
+    return {
+        "id": entry.id,
+        "created_at": _format_date(entry.created_at),
+        "last_modified": _format_date(entry.last_modified),
+        "downloads": entry.downloads,
+        "likes": entry.likes,
+        "tags": entry.tags,
+        "readme": readme_content,
+    }
+
+
+def _format_entries(entries: List[DatasetInfo]) -> str:
+    clean_entries: List[Dict[str, Any]] = [_clean_entry(entry) for entry in entries]
+    return json.dumps({"results": clean_entries}, ensure_ascii=False)
+
+
+def hf_datasets_search(
+    query: Optional[str] = None,
+    search_filter: Optional[List[str]] = None,
+    limit: Optional[int] = 5,
+    sort_by: Optional[str] = "trending_score",
+    sort_order: Optional[str] = "descending",
+) -> str:
+    """
+    Search or filter HF datasets.
+
+    Examples:
+        List only the datasets in Russian for language modeling:
+        hf_datasets_search(filter=(language:ru", "task_ids:language-modeling"))
+
+        List all recent datasets with "text" in their name
+        hf_datasets_search(query="text", sort_by="last_modified")
+
+    Returns a JSON object serialized to a string. The structure is: {"results": [...]}
+    Every item in the "results" has the following fields:
+    ("id", "created_at", "last_modified", "downloads", "likes", "tags")
+    Use `json.loads` to deserialize the result if you want to get specific fields.
+
+    Args:
+        query: The search query for the exact match search.
+        search_filter: A list of string to filter datasets.
+        limit: The maximum number of items to return. limit=5 by default, limit=10 is the maximum.
+        sort_by:
+            The key with which to sort the resulting models.
+            Possible values are "last_modified", "trending_score", "created_at", "downloads" and "likes".
+            "trending_score" by default.
+        sort_order: 2 sort orders: ascending, descending. descending by default.
+    """
+    direction: Optional[Literal[-1]] = -1 if sort_order == "descending" else None
+    results = list(
+        HF_API.list_datasets(
+            search=query,
+            sort=sort_by,
+            direction=direction,
+            limit=limit,
+            filter=search_filter,
+        )
+    )
+    return _format_entries(results)

academia_mcp/tools/s2_citations.py

@@ -0,0 +1,118 @@
+# Based on
+# https://api.semanticscholar.org/api-docs/graph#tag/Paper-Data/operation/get_graph_get_paper_citations
+
+import json
+from typing import Optional, List, Dict, Any
+from urllib3.util.retry import Retry
+
+import requests
+
+OLD_API_URL_TEMPLATE = "https://api.semanticscholar.org/v1/paper/{paper_id}"
+GRAPH_URL_TEMPLATE = "https://api.semanticscholar.org/graph/v1/paper/{paper_id}/citations?fields={fields}&offset={offset}&limit={limit}"
+FIELDS = "title,authors,externalIds,venue,citationCount,publicationDate"
+
+
+def _get_results(url: str) -> requests.Response:
+    retry_strategy = Retry(
+        total=3,
+        backoff_factor=30,
+        status_forcelist=[429, 500, 502, 503, 504],
+        allowed_methods=["GET"],
+    )
+
+    session = requests.Session()
+    adapter = requests.adapters.HTTPAdapter(max_retries=retry_strategy)
+    session.mount("https://", adapter)
+
+    try:
+        response = session.get(url, timeout=30)
+        response.raise_for_status()
+        return response
+    except (
+        requests.exceptions.ConnectionError,
+        requests.exceptions.RequestException,
+        requests.exceptions.HTTPError,
+    ) as e:
+        print(f"Failed after {retry_strategy.total} retries: {str(e)}")
+        raise
+
+    return response
+
+
+def _format_authors(authors: List[Dict[str, Any]]) -> List[str]:
+    return [a["name"] for a in authors]
+
+
+def _clean_entry(entry: Dict[str, Any]) -> Dict[str, Any]:
+    entry = entry["citingPaper"]
+    external_ids = entry.get("externalIds")
+    if not external_ids:
+        external_ids = dict()
+    external_ids.pop("CorpusId", None)
+    arxiv_id = external_ids.pop("ArXiv", None)
+    return {
+        "arxiv_id": arxiv_id,
+        "external_ids": external_ids if external_ids else None,
+        "title": entry["title"],
+        "authors": _format_authors(entry["authors"]),
+        "venue": entry.get("venue", ""),
+        "citation_count": entry.get("citationCount", 0),
+        "publication_date": entry.get("publicationDate", ""),
+    }
+
+
+def _format_entries(
+    entries: List[Dict[str, Any]],
+    start_index: int,
+    total_results: int,
+) -> str:
+    clean_entries = [_clean_entry(e) for e in entries]
+    return json.dumps(
+        {
+            "total_count": total_results,
+            "returned_count": len(entries),
+            "offset": start_index,
+            "results": clean_entries,
+        },
+        ensure_ascii=False,
+    )
+
+
+def s2_citations(
+    arxiv_id: str,
+    offset: Optional[int] = 0,
+    limit: Optional[int] = 50,
+) -> str:
+    """
+    Get all papers that cited a given arXiv paper based on Semantic Scholar info.
+
+    Returns a JSON object serialized to a string. The structure is:
+    {"total_count": ..., "returned_count": ..., "offset": ..., "results": [...]}
+    Every item in the "results" has the following fields:
+    ("arxiv_id", "external_ids", "title", "authors", "venue", "citation_count", "publication_date")
+    Use `json.loads` to deserialize the result if you want to get specific fields.
+
+    Args:
+        arxiv_id: The ID of a given arXiv paper.
+        offset: The offset to scroll through citations. 10 items will be skipped if offset=10. 0 by default.
+        limit: The maximum number of items to return. limit=50 by default.
+    """
+
+    assert isinstance(arxiv_id, str), "Error: Your arxiv_id must be a string"
+    if "v" in arxiv_id:
+        arxiv_id = arxiv_id.split("v")[0]
+    paper_id = f"arxiv:{arxiv_id}"
+
+    url = GRAPH_URL_TEMPLATE.format(paper_id=paper_id, fields=FIELDS, offset=offset, limit=limit)
+    response = _get_results(url)
+    result = response.json()
+    entries = result["data"]
+    total_count = len(result["data"]) + result["offset"]
+
+    if "next" in result:
+        paper_url = OLD_API_URL_TEMPLATE.format(paper_id=paper_id)
+        paper_response = _get_results(paper_url)
+        paper_result = paper_response.json()
+        total_count = paper_result["numCitedBy"]
+
+    return _format_entries(entries, offset if offset else 0, total_count)

academia_mcp-0.0.2.dist-info/METADATA

@@ -0,0 +1,33 @@
+Metadata-Version: 2.4
+Name: academia-mcp
+Version: 0.0.2
+Summary: MCP server that provides different tools to search for scientific publications
+Author-email: Ilya Gusev <phoenixilya@gmail.com>
+Project-URL: Homepage, https://github.com/IlyaGusev/academia_mcp
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: mcp==1.9.2
+Requires-Dist: xmltodict>=0.14.0
+Requires-Dist: types-xmltodict>=0.14.0
+Requires-Dist: requests>=2.32.0
+Requires-Dist: types-requests>=2.32.0
+Requires-Dist: pypdf>=5.1.0
+Requires-Dist: beautifulsoup4>=4.12.0
+Requires-Dist: types-beautifulsoup4>=4.12.0
+Requires-Dist: markdownify==0.14.1
+Requires-Dist: acl-anthology==0.5.2
+Requires-Dist: markdown==3.7.0
+Requires-Dist: types-markdown==3.7.0.20250322
+Requires-Dist: black==25.1.0
+Requires-Dist: mypy==1.16.0
+Requires-Dist: flake8==7.2.0
+Requires-Dist: huggingface-hub>=0.32.4
+Dynamic: license-file
+
+# Academia MCP
+
+A collection of MCP tools related to the search of scientific papers.

academia_mcp-0.0.2.dist-info/RECORD

@@ -0,0 +1,15 @@
+academia_mcp/__init__.py,sha256=0wvKJeTFVLXWx97eL76D6SRNF4o5IUxwv83lWiG3Xiw,89
+academia_mcp/__main__.py,sha256=rcmsOtJd3SA82exjrcGBuxuptcoxF8AXI7jNjiVq2BY,59
+academia_mcp/server.py,sha256=2OIyYdrKZ4bKwgywAYg4iswicIezgm5Qqa7TYluePB4,532
+academia_mcp/tools/__init__.py,sha256=KZuteEnRZSJFl1E_VIH7V3hAHS6WUl-K4Ge41D9q58M,347
+academia_mcp/tools/anthology_search.py,sha256=Wnpd6ovSeCYXjuzisV37hg_Kdh4NVC_1Y93VLIy2Gus,7728
+academia_mcp/tools/arxiv_download.py,sha256=fJ1PCgnpQvPKXv6VLKLcL_Hd_hz9LhPM-NAq3gYehGk,11158
+academia_mcp/tools/arxiv_search.py,sha256=-A5-7PP-kYgjQjMreRGKkOwD4AQf7nVt6yh8vHsFSo4,9048
+academia_mcp/tools/hf_datasets_search.py,sha256=KiBkqT4rXjEN4oc1AWZOPnqN_Go90TQogY5-DUm3LQo,2854
+academia_mcp/tools/s2_citations.py,sha256=xIwaGaAcLNBJ8_IAJtFiN2h_164yvz_jcsl6c-wFzAA,3988
+academia_mcp-0.0.2.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+academia_mcp-0.0.2.dist-info/METADATA,sha256=p89qDQZQ_m2sgKBgKZYfAKBaFnciP0SfHNqSVZlTn6c,1150
+academia_mcp-0.0.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+academia_mcp-0.0.2.dist-info/entry_points.txt,sha256=gxkiKJ74w2FwJpSECpjA3XtCfI5ZfrM6N8cqnwsq4yY,51
+academia_mcp-0.0.2.dist-info/top_level.txt,sha256=CzGpRFsRRJRqWEb1e3SUlcfGqRzOxevZGaJWrtGF8W0,13
+academia_mcp-0.0.2.dist-info/RECORD,,

academia_mcp-0.0.2.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

academia_mcp-0.0.2.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+academia_mcp = academia_mcp:main

academia_mcp-0.0.2.dist-info/licenses/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

academia_mcp-0.0.2.dist-info/top_level.txt

@@ -0,0 +1 @@
+academia_mcp