academia-mcp 1.8.0__tar.gz → 1.9.0__tar.gz

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: academia-mcp
-Version: 1.8.0
+Version: 1.9.0
 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
@@ -29,6 +29,7 @@ Requires-Dist: jinja2>=3.1.6
 Requires-Dist: datasets>=4.0.0
 Requires-Dist: pymupdf>=1.26.4
 Requires-Dist: pillow>=11.3.0
+Requires-Dist: pydantic-settings>=2.6.0
 Dynamic: license-file
 
 # Academia MCP

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/academia_mcp/files.py

@@ -1,7 +1,8 @@
-import os
 from typing import Optional
 from pathlib import Path
 
+from academia_mcp.settings import settings
+
 DIR_PATH = Path(__file__).parent
 ROOT_PATH = DIR_PATH.parent
 DEFAULT_WORKSPACE_DIR_PATH: Path = DIR_PATH / "workdir"
@@ -14,7 +15,7 @@ class WorkspaceDirectory:
     @classmethod
     def get_dir(cls) -> Path:
         if cls.workspace_dir is None:
-            return Path(os.getenv("WORKSPACE_DIR", DEFAULT_WORKSPACE_DIR_PATH))
+            return Path(settings.WORKSPACE_DIR)
         return cls.workspace_dir
 
     @classmethod

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/academia_mcp/llm.py

@@ -1,10 +1,11 @@
-import os
 from typing import List, Dict, Any
 
 from pydantic import BaseModel
 from openai import AsyncOpenAI
 from openai.types.chat.chat_completion_message import ChatCompletionMessage
 
+from academia_mcp.settings import settings
+
 
 class ChatMessage(BaseModel):  # type: ignore
     role: str
@@ -15,9 +16,9 @@ ChatMessages = List[ChatMessage]
 
 
 async def llm_acall(model_name: str, messages: ChatMessages, **kwargs: Any) -> str:
-    key = os.getenv("OPENROUTER_API_KEY", "")
+    key = settings.OPENROUTER_API_KEY
     assert key, "Please set OPENROUTER_API_KEY in the environment variables"
-    base_url = os.getenv("BASE_URL", "https://openrouter.ai/api/v1")
+    base_url = settings.BASE_URL
 
     client = AsyncOpenAI(base_url=base_url, api_key=key)
     response: ChatCompletionMessage = (

academia_mcp-1.9.0/academia_mcp/server.py

@@ -0,0 +1,126 @@
+import socket
+import logging
+from logging.config import dictConfig
+from typing import Optional, Literal
+
+import fire  # type: ignore
+from mcp.server.fastmcp import FastMCP
+from uvicorn.config import LOGGING_CONFIG as UVICORN_LOGGING_CONFIG
+
+from academia_mcp.settings import settings
+from academia_mcp.tools.arxiv_search import arxiv_search
+from academia_mcp.tools.arxiv_download import arxiv_download
+from academia_mcp.tools.s2_citations import s2_get_citations, s2_get_references
+from academia_mcp.tools.hf_datasets_search import hf_datasets_search
+from academia_mcp.tools.anthology_search import anthology_search
+from academia_mcp.tools.document_qa import document_qa
+from academia_mcp.tools.latex import (
+    compile_latex,
+    get_latex_template,
+    get_latex_templates_list,
+    read_pdf,
+)
+from academia_mcp.tools.web_search import (
+    web_search,
+    tavily_web_search,
+    exa_web_search,
+    brave_web_search,
+)
+from academia_mcp.tools.visit_webpage import visit_webpage
+from academia_mcp.tools.bitflip import (
+    extract_bitflip_info,
+    generate_research_proposals,
+    score_research_proposals,
+)
+from academia_mcp.tools.review import review_pdf_paper, download_pdf_paper
+
+
+def configure_uvicorn_style_logging(level: int = logging.INFO) -> None:
+    config = {**UVICORN_LOGGING_CONFIG}
+    config["disable_existing_loggers"] = False
+    config["root"] = {"handlers": ["default"], "level": logging.getLevelName(level)}
+    dictConfig(config)
+
+
+def find_free_port() -> int:
+    for port in range(5000, 6001):
+        try:
+            with socket.socket() as s:
+                s.bind(("", port))
+                return port
+        except Exception:
+            continue
+    raise RuntimeError("No free port in range 5000-6000 found")
+
+
+def run(
+    host: str = "0.0.0.0",
+    port: Optional[int] = None,
+    mount_path: str = "/",
+    streamable_http_path: str = "/mcp",
+    transport: Literal["stdio", "sse", "streamable-http"] = "streamable-http",
+    disable_web_search_tools: bool = False,
+    disable_llm_tools: bool = False,
+) -> None:
+    configure_uvicorn_style_logging()
+    server = FastMCP(
+        "Academia MCP",
+        stateless_http=True,
+        streamable_http_path=streamable_http_path,
+        mount_path=mount_path,
+    )
+    logger = logging.getLogger(__name__)
+
+    server.add_tool(arxiv_search)
+    server.add_tool(arxiv_download)
+    server.add_tool(s2_get_citations)
+    server.add_tool(s2_get_references)
+    server.add_tool(hf_datasets_search)
+    server.add_tool(anthology_search)
+    server.add_tool(get_latex_template)
+    server.add_tool(get_latex_templates_list)
+    server.add_tool(visit_webpage)
+
+    if settings.WORKSPACE_DIR:
+        server.add_tool(compile_latex)
+        server.add_tool(download_pdf_paper)
+        server.add_tool(read_pdf)
+    else:
+        logger.warning(
+            "WORKSPACE_DIR is not set, compile_latex/download_pdf_paper/read_pdf will not be available!"
+        )
+
+    if not disable_web_search_tools:
+        if settings.TAVILY_API_KEY:
+            server.add_tool(tavily_web_search)
+        if settings.EXA_API_KEY:
+            server.add_tool(exa_web_search)
+        if settings.BRAVE_API_KEY:
+            server.add_tool(brave_web_search)
+        if settings.EXA_API_KEY or settings.BRAVE_API_KEY or settings.TAVILY_API_KEY:
+            server.add_tool(web_search)
+        else:
+            logger.warning("No web search tools keys are set, web_search will not be available!")
+
+    if not disable_llm_tools and settings.OPENROUTER_API_KEY:
+        server.add_tool(extract_bitflip_info)
+        server.add_tool(generate_research_proposals)
+        server.add_tool(score_research_proposals)
+        server.add_tool(document_qa)
+        if settings.WORKSPACE_DIR:
+            server.add_tool(review_pdf_paper)
+    else:
+        logger.warning("No OpenRouter API key is set, LLM-related tools will not be available!")
+
+    if port is None:
+        if settings.PORT is not None:
+            port = int(settings.PORT)
+        else:
+            port = find_free_port()
+    server.settings.port = port
+    server.settings.host = host
+    server.run(transport=transport)
+
+
+if __name__ == "__main__":
+    fire.Fire(run)

academia_mcp-1.9.0/academia_mcp/settings.py

@@ -0,0 +1,33 @@
+from pathlib import Path
+from typing import Optional
+
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+
+class Settings(BaseSettings):
+    BASE_URL: str = "https://openrouter.ai/api/v1"
+
+    OPENROUTER_API_KEY: str = ""
+    TAVILY_API_KEY: Optional[str] = None
+    EXA_API_KEY: Optional[str] = None
+    BRAVE_API_KEY: Optional[str] = None
+
+    REVIEW_MODEL_NAME: str = "gpt-5"
+    BITFLIP_MODEL_NAME: str = "deepseek/deepseek-chat-v3-0324"
+    BITFLIP_MAX_COMPLETION_TOKENS: int = 16384
+    DOCUMENT_QA_MODEL_NAME: str = "deepseek/deepseek-chat-v3-0324"
+    DOCUMENT_QA_QUESTION_MAX_LENGTH: int = 10000
+    DOCUMENT_QA_DOCUMENT_MAX_LENGTH: int = 200000
+
+    PORT: int = 5056
+    WORKSPACE_DIR: Optional[Path] = None
+
+    model_config = SettingsConfigDict(
+        env_file=".env",
+        env_file_encoding="utf-8",
+        env_prefix="",
+        extra="ignore",
+    )
+
+
+settings = Settings()

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/academia_mcp/tools/__init__.py

@@ -5,8 +5,7 @@ from .hf_datasets_search import hf_datasets_search
 from .s2_citations import s2_get_references, s2_get_citations
 from .document_qa import document_qa
 from .latex import (
-    compile_latex_from_file,
-    compile_latex_from_str,
+    compile_latex,
     get_latex_template,
     get_latex_templates_list,
     read_pdf,
@@ -14,7 +13,7 @@ from .latex import (
 from .web_search import web_search, tavily_web_search, exa_web_search, brave_web_search
 from .visit_webpage import visit_webpage
 from .bitflip import extract_bitflip_info, generate_research_proposals, score_research_proposals
-from .review import review_pdf_paper, download_pdf_paper
+from .review import review_pdf_paper, download_pdf_paper, review_pdf_paper_by_url
 
 __all__ = [
     "arxiv_search",
@@ -24,8 +23,7 @@ __all__ = [
     "s2_get_citations",
     "hf_datasets_search",
     "document_qa",
-    "compile_latex_from_file",
-    "compile_latex_from_str",
+    "compile_latex",
     "get_latex_template",
     "get_latex_templates_list",
     "web_search",
@@ -37,6 +35,7 @@ __all__ = [
     "generate_research_proposals",
     "score_research_proposals",
     "review_pdf_paper",
+    "review_pdf_paper_by_url",
     "download_pdf_paper",
     "read_pdf",
 ]

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/academia_mcp/tools/bitflip.py

@@ -2,7 +2,6 @@
 # https://web.stanford.edu/class/cs197c/slides/02-literature-search.pdf
 
 import json
-import os
 import random
 from typing import List, Optional, Any, Dict
 
@@ -12,6 +11,7 @@ from datasets import load_dataset  # type: ignore
 from academia_mcp.tools.arxiv_download import arxiv_download
 from academia_mcp.utils import extract_json, encode_prompt
 from academia_mcp.llm import llm_acall, ChatMessage
+from academia_mcp.settings import settings
 
 
 class ProposalDataset:
@@ -201,7 +201,7 @@ async def extract_bitflip_info(arxiv_id: str) -> str:
     Args:
         arxiv_id: The arXiv ID of the paper to extract the Bit-Flip information from.
     """
-    model_name = os.getenv("BITFLIP_MODEL_NAME", "deepseek/deepseek-chat-v3-0324")
+    model_name = settings.BITFLIP_MODEL_NAME
     paper = arxiv_download(arxiv_id)
     abstract = json.loads(paper)["abstract"]
     prompt = encode_prompt(EXTRACT_PROMPT, abstract=abstract)
@@ -240,8 +240,8 @@ async def generate_research_proposals(
     ]
     Use `json.loads` to deserialize the result if you want to get specific items.
     """
-    model_name = os.getenv("BITFLIP_MODEL_NAME", "deepseek/deepseek-chat-v3-0324")
-    max_completion_tokens = int(os.getenv("BITFLIP_MAX_COMPLETION_TOKENS", 16384))
+    model_name = settings.BITFLIP_MODEL_NAME
+    max_completion_tokens = int(settings.BITFLIP_MAX_COMPLETION_TOKENS)
     examples = ProposalDataset.get_dataset()[:]
     examples = random.choices(examples, k=2)
 
@@ -293,7 +293,7 @@ async def score_research_proposals(proposals: str | List[str | Dict[str, Any] |
     Args:
         proposals: A list of JSON strings with research proposals.
     """
-    model_name = os.getenv("BITFLIP_MODEL_NAME", "deepseek/deepseek-chat-v3-0324")
+    model_name = settings.BITFLIP_MODEL_NAME
     if isinstance(proposals, str):
         proposals = json.loads(proposals)
         assert isinstance(proposals, list), "Proposals should be a list of JSON strings"

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/academia_mcp/tools/document_qa.py

@@ -1,14 +1,12 @@
-import os
 import json
 from typing import List, Any, Dict
-from dotenv import load_dotenv
 
 from pydantic import BaseModel
 
 from academia_mcp.llm import llm_acall
 from academia_mcp.utils import truncate_content
+from academia_mcp.settings import settings
 
-load_dotenv()
 
 PROMPT = """You are a helpful assistant that answers questions about documents accurately and concisely.
 Please answer the following questions based solely on the provided document.
@@ -65,10 +63,10 @@ async def document_qa(
         document = json.dumps(document)
     assert document and document.strip(), "Please provide non-empty 'document'"
 
-    question = truncate_content(question, 10000)
-    document = truncate_content(document, 200000)
+    question = truncate_content(question, settings.DOCUMENT_QA_QUESTION_MAX_LENGTH)
+    document = truncate_content(document, settings.DOCUMENT_QA_DOCUMENT_MAX_LENGTH)
 
-    model_name = os.getenv("DOCUMENT_QA_MODEL_NAME", "deepseek/deepseek-chat-v3-0324")
+    model_name = settings.DOCUMENT_QA_MODEL_NAME
     prompt = PROMPT.format(question=question, document=document)
     content = await llm_acall(
         model_name=model_name, messages=[ChatMessage(role="user", content=prompt)]

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/academia_mcp/tools/latex.py

@@ -46,7 +46,7 @@ def get_latex_template(template_name: str) -> str:
     return json.dumps({"template": template_path.read_text(), "style": style_path.read_text()})
 
 
-def compile_latex_from_file(
+def compile_latex(
     input_filename: str, output_filename: str = "output.pdf", timeout: int = 60
 ) -> str:
     """
@@ -63,24 +63,8 @@ def compile_latex_from_file(
     if not input_filename_path.exists():
         input_filename_path = Path(get_workspace_dir()) / input_filename
     assert input_filename_path.exists(), f"Input file {input_filename} does not exist"
-    with open(input_filename_path, "r", encoding="utf-8") as file:
-        latex_code = file.read()
-    return compile_latex_from_str(latex_code, output_filename, timeout)
+    latex_code = input_filename_path.read_text(encoding="utf-8")
 
-
-def compile_latex_from_str(
-    latex_code: str, output_filename: str = "output.pdf", timeout: int = 60
-) -> str:
-    """
-    Compile a latex code.
-
-    Returns a string with the result of the compilation.
-
-    Args:
-        latex_code: The latex code to compile.
-        output_filename: The path to the output pdf file.
-        timeout: The timeout for the compilation. 60 seconds by default.
-    """
     if shutil.which("pdflatex") is None:
         return "pdflatex is not installed or not found in PATH."
 
@@ -116,6 +100,13 @@ def compile_latex_from_str(
             except Exception:
                 pass
 
+            try:
+                bib_source_path = input_filename_path.parent / "references.bib"
+                if bib_source_path.exists():
+                    shutil.copyfile(bib_source_path, temp_dir_path / "references.bib")
+            except Exception:
+                pass
+
             try:
                 subprocess.run(
                     [

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/academia_mcp/tools/review.py

@@ -1,6 +1,6 @@
 import base64
-import os
 import uuid
+import tempfile
 from io import BytesIO
 from pathlib import Path
 from typing import List, Dict, Any
@@ -8,6 +8,7 @@ from typing import List, Dict, Any
 from academia_mcp.pdf import parse_pdf_file_to_images, parse_pdf_file, download_pdf
 from academia_mcp.llm import llm_acall, ChatMessage
 from academia_mcp.files import get_workspace_dir
+from academia_mcp.settings import settings
 
 
 PROMPT = """
@@ -138,6 +139,16 @@ Always produce a correct JSON object.
 """
 
 
+def _create_pdf_filename(pdf_url: str) -> str:
+    if "arxiv.org/pdf" in pdf_url:
+        pdf_filename = pdf_url.split("/")[-1]
+    else:
+        pdf_filename = str(uuid.uuid4())
+    if not pdf_filename.endswith(".pdf"):
+        pdf_filename += ".pdf"
+    return pdf_filename
+
+
 def download_pdf_paper(pdf_url: str) -> str:
     """
     Download a pdf file from a url to the workspace directory.
@@ -147,13 +158,7 @@ def download_pdf_paper(pdf_url: str) -> str:
     Args:
         pdf_url: The url of the pdf file.
     """
-    if "arxiv.org/pdf" in pdf_url:
-        pdf_filename = pdf_url.split("/")[-1]
-    else:
-        pdf_filename = str(uuid.uuid4())
-    if not pdf_filename.endswith(".pdf"):
-        pdf_filename += ".pdf"
-
+    pdf_filename = _create_pdf_filename(pdf_url)
     pdf_path = Path(get_workspace_dir()) / pdf_filename
     download_pdf(pdf_url, pdf_path)
     return pdf_filename
@@ -198,7 +203,7 @@ async def review_pdf_paper(pdf_filename: str) -> str:
             "text": "####\n\nInstructions:\n\n" + PROMPT,
         }
     )
-    model_name = os.getenv("REVIEW_MODEL_NAME", "gpt-5")
+    model_name = settings.REVIEW_MODEL_NAME
     llm_response = await llm_acall(
         model_name=model_name,
         messages=[
@@ -206,3 +211,21 @@ async def review_pdf_paper(pdf_filename: str) -> str:
         ],
     )
     return llm_response.strip()
+
+
+async def review_pdf_paper_by_url(pdf_url: str) -> str:
+    """
+    Review a pdf file with a paper by url.
+    It downloads the pdf file and then reviews it.
+    It parses the pdf file into images and then sends the images to the LLM for review.
+    It can detect different issues with the paper formatting.
+    Returns a proper NeurIPS-style review.
+
+    Args:
+        pdf_url: The url of the pdf file.
+    """
+    pdf_filename = _create_pdf_filename(pdf_url)
+    with tempfile.TemporaryDirectory(prefix="temp_pdf_") as temp_dir:
+        pdf_path = Path(temp_dir) / pdf_filename
+        download_pdf(pdf_url, pdf_path)
+        return await review_pdf_paper(str(pdf_path))

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/academia_mcp/tools/visit_webpage.py

@@ -1,18 +1,18 @@
 import re
-import os
 import json
 from typing import Optional
 
 from markdownify import markdownify  # type: ignore
 
 from academia_mcp.utils import get_with_retries, post_with_retries
+from academia_mcp.settings import settings
 
 EXA_CONTENTS_URL = "https://api.exa.ai/contents"
 AVAILABLE_PROVIDERS = ("basic", "exa")
 
 
 def _exa_visit_webpage(url: str) -> str:
-    key = os.getenv("EXA_API_KEY", "")
+    key = settings.EXA_API_KEY or ""
     assert key, "Error: EXA_API_KEY is not set and no api_key was provided"
     payload = {
         "urls": [url],
@@ -38,14 +38,14 @@ def visit_webpage(url: str, provider: Optional[str] = "basic") -> str:
         provider in AVAILABLE_PROVIDERS
     ), f"Invalid provider: {provider}. Available providers: {AVAILABLE_PROVIDERS}"
 
-    if provider == "exa":
+    if provider == "exa" and settings.EXA_API_KEY:
         return _exa_visit_webpage(url)
 
     assert provider == "basic"
     response = get_with_retries(url)
     content_type = response.headers.get("content-type", "").lower()
     if not content_type or (not content_type.startswith("text/") and "html" not in content_type):
-        if os.getenv("EXA_API_KEY"):
+        if settings.EXA_API_KEY:
             return _exa_visit_webpage(url)
         return json.dumps(
             {"id": url, "error": f"Unsupported content-type: {content_type or 'unknown'}"}

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/academia_mcp/tools/web_search.py

@@ -1,8 +1,8 @@
-import os
 import json
 from typing import Optional
 
 from academia_mcp.utils import post_with_retries, get_with_retries
+from academia_mcp.settings import settings
 
 
 EXA_SEARCH_URL = "https://api.exa.ai/search"
@@ -32,9 +32,9 @@ def web_search(
     providers = ("tavily", "brave", "exa")
     assert provider in providers, "Error: provider must be either 'exa', 'tavily' or 'brave'"
 
-    is_tavily_available = os.getenv("TAVILY_API_KEY") is not None
-    is_exa_available = os.getenv("EXA_API_KEY") is not None
-    is_brave_available = os.getenv("BRAVE_API_KEY") is not None
+    is_tavily_available = bool(settings.TAVILY_API_KEY)
+    is_exa_available = bool(settings.EXA_API_KEY)
+    is_brave_available = bool(settings.BRAVE_API_KEY)
     assert is_tavily_available or is_exa_available or is_brave_available
     availability = {
         "tavily": is_tavily_available,
@@ -76,7 +76,7 @@ def tavily_web_search(query: str, limit: Optional[int] = 20) -> str:
     assert isinstance(limit, int), "Error: limit should be an integer"
     assert 0 < limit <= 25, "Error: limit should be between 1 and 25"
 
-    key = os.getenv("TAVILY_API_KEY", "")
+    key = settings.TAVILY_API_KEY or ""
     assert key, "Error: TAVILY_API_KEY is not set and no api_key was provided"
     payload = {
         "query": query,
@@ -112,7 +112,7 @@ def exa_web_search(query: str, limit: Optional[int] = 20) -> str:
     assert isinstance(limit, int), "Error: limit should be an integer"
     assert 0 < limit <= 25, "Error: limit should be between 1 and 25"
 
-    key = os.getenv("EXA_API_KEY", "")
+    key = settings.EXA_API_KEY or ""
     assert key, "Error: EXA_API_KEY is not set and no api_key was provided"
     payload = {
         "query": query,
@@ -151,7 +151,7 @@ def brave_web_search(query: str, limit: Optional[int] = 20) -> str:
     assert isinstance(limit, int), "Error: limit should be an integer"
     assert 0 < limit <= 20, "Error: limit should be between 1 and 20"
 
-    key = os.getenv("BRAVE_API_KEY", "")
+    key = settings.BRAVE_API_KEY or ""
     assert key, "Error: BRAVE_API_KEY is not set and no api_key was provided"
     payload = {
         "q": query,

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/academia_mcp.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: academia-mcp
-Version: 1.8.0
+Version: 1.9.0
 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
@@ -29,6 +29,7 @@ Requires-Dist: jinja2>=3.1.6
 Requires-Dist: datasets>=4.0.0
 Requires-Dist: pymupdf>=1.26.4
 Requires-Dist: pillow>=11.3.0
+Requires-Dist: pydantic-settings>=2.6.0
 Dynamic: license-file
 
 # Academia MCP

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/academia_mcp.egg-info/SOURCES.txt

@@ -8,6 +8,7 @@ academia_mcp/llm.py
 academia_mcp/pdf.py
 academia_mcp/py.typed
 academia_mcp/server.py
+academia_mcp/settings.py
 academia_mcp/utils.py
 academia_mcp.egg-info/PKG-INFO
 academia_mcp.egg-info/SOURCES.txt

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/academia_mcp.egg-info/requires.txt

@@ -17,3 +17,4 @@ jinja2>=3.1.6
 datasets>=4.0.0
 pymupdf>=1.26.4
 pillow>=11.3.0
+pydantic-settings>=2.6.0

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "academia-mcp"
-version = "1.8.0"
+version = "1.9.0"
 description = "MCP server that provides different tools to search for scientific publications"
 readme = "README.md"
 authors = [
@@ -36,6 +36,7 @@ dependencies = [
     "datasets>=4.0.0",
     "pymupdf>=1.26.4",
     "pillow>=11.3.0",
+    "pydantic-settings>=2.6.0",
 ]
 
 [dependency-groups]
@@ -78,4 +79,5 @@ filterwarnings = [
     "ignore:builtin type SwigPyObject has no __module__ attribute:DeprecationWarning",
     "ignore:builtin type swigvarlink has no __module__ attribute:DeprecationWarning",
     "ignore:The 'warn' method is deprecated, use 'warning' instead:DeprecationWarning:acl_anthology.text.texmath",
+    "ignore:Data directory contains a different schema.rnc as this library; you might need to update the data or the acl-anthology library.",
 ]

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/tests/test_latex.py

@@ -3,8 +3,7 @@ import tempfile
 from pathlib import Path
 
 from academia_mcp.tools.latex import (
-    compile_latex_from_file,
-    compile_latex_from_str,
+    compile_latex,
     get_latex_template,
     get_latex_templates_list,
     read_pdf,
@@ -25,12 +24,6 @@ def test_latex_get_latex_template() -> None:
     assert result["style"] is not None
 
 
-def test_latex_compile_latex_from_str() -> None:
-    template = json.loads(get_latex_template("agents4science_2025"))
-    result = compile_latex_from_str(template["template"], "test.pdf")
-    assert "Compilation successful" in result
-
-
 def test_latex_compile_latex_from_file() -> None:
     template = json.loads(get_latex_template("agents4science_2025"))
     with tempfile.TemporaryDirectory() as temp_dir:
@@ -39,7 +32,7 @@ def test_latex_compile_latex_from_file() -> None:
         tex_file_path = temp_dir_path / tex_filename
         pdf_filename = "test.pdf"
         tex_file_path.write_text(template["template"], encoding="utf-8")
-        result = compile_latex_from_file(str(tex_file_path), pdf_filename)
+        result = compile_latex(str(tex_file_path), pdf_filename)
     assert "Compilation successful" in result
 
 
@@ -51,13 +44,7 @@ def test_latex_read_pdf() -> None:
         tex_file_path = temp_dir_path / tex_filename
         pdf_filename = "test.pdf"
         tex_file_path.write_text(template["template"], encoding="utf-8")
-        compile_latex_from_file(str(tex_file_path), pdf_filename)
+        compile_latex(str(tex_file_path), pdf_filename)
         read_result = json.loads(read_pdf(pdf_filename))
         assert read_result
         assert "Page 1" in read_result[0]
-
-
-def test_latex_compile_latex_error() -> None:
-    template = json.loads(get_latex_template("agents4science_2025"))
-    result = compile_latex_from_str(template["template"][:100], "test.pdf")
-    print(result)

{academia_mcp-1.8.0 → academia_mcp-1.9.0}/tests/test_review.py

@@ -1,7 +1,13 @@
-from academia_mcp.tools.review import review_pdf_paper, download_pdf_paper
+from academia_mcp.tools.review import review_pdf_paper, download_pdf_paper, review_pdf_paper_by_url
 
 
 async def test_review_pdf_paper() -> None:
     download_pdf_paper("https://arxiv.org/pdf/2502.01220")
     review = await review_pdf_paper("2502.01220.pdf")
     assert review
+
+
+async def test_review_pdf_paper_by_url() -> None:
+    review = await review_pdf_paper_by_url("https://arxiv.org/pdf/2502.01220")
+    assert review
+    assert "format_issues" in str(review)

academia_mcp-1.8.0/academia_mcp/server.py

@@ -1,103 +0,0 @@
-import os
-import socket
-from typing import Optional, Literal
-
-import fire  # type: ignore
-from mcp.server.fastmcp import FastMCP
-from dotenv import load_dotenv
-
-from .tools.arxiv_search import arxiv_search
-from .tools.arxiv_download import arxiv_download
-from .tools.s2_citations import s2_get_citations, s2_get_references
-from .tools.hf_datasets_search import hf_datasets_search
-from .tools.anthology_search import anthology_search
-from .tools.document_qa import document_qa
-from .tools.latex import (
-    compile_latex_from_file,
-    compile_latex_from_str,
-    get_latex_template,
-    get_latex_templates_list,
-    read_pdf,
-)
-from .tools.web_search import web_search, tavily_web_search, exa_web_search, brave_web_search
-from .tools.visit_webpage import visit_webpage
-from .tools.bitflip import (
-    extract_bitflip_info,
-    generate_research_proposals,
-    score_research_proposals,
-)
-from .tools.review import review_pdf_paper, download_pdf_paper
-
-
-load_dotenv()
-
-
-def find_free_port() -> int:
-    for port in range(5000, 6001):
-        try:
-            with socket.socket() as s:
-                s.bind(("", port))
-                return port
-        except Exception:
-            continue
-    raise RuntimeError("No free port in range 5000-6000 found")
-
-
-def run(
-    host: str = "0.0.0.0",
-    port: Optional[int] = None,
-    mount_path: str = "/",
-    streamable_http_path: str = "/mcp",
-    transport: Literal["stdio", "sse", "streamable-http"] = "streamable-http",
-    disable_web_search_tools: bool = False,
-    disable_llm_tools: bool = False,
-) -> None:
-    server = FastMCP(
-        "Academia MCP",
-        stateless_http=True,
-        streamable_http_path=streamable_http_path,
-        mount_path=mount_path,
-    )
-
-    server.add_tool(arxiv_search)
-    server.add_tool(arxiv_download)
-    server.add_tool(s2_get_citations)
-    server.add_tool(s2_get_references)
-    server.add_tool(hf_datasets_search)
-    server.add_tool(anthology_search)
-    server.add_tool(compile_latex_from_file)
-    server.add_tool(compile_latex_from_str)
-    server.add_tool(get_latex_template)
-    server.add_tool(get_latex_templates_list)
-    server.add_tool(visit_webpage)
-    server.add_tool(download_pdf_paper)
-    server.add_tool(read_pdf)
-
-    if not disable_web_search_tools:
-        if os.getenv("TAVILY_API_KEY"):
-            server.add_tool(tavily_web_search)
-        if os.getenv("EXA_API_KEY"):
-            server.add_tool(exa_web_search)
-        if os.getenv("BRAVE_API_KEY"):
-            server.add_tool(brave_web_search)
-        if os.getenv("EXA_API_KEY") or os.getenv("BRAVE_API_KEY") or os.getenv("TAVILY_API_KEY"):
-            server.add_tool(web_search)
-
-    if not disable_llm_tools and os.getenv("OPENROUTER_API_KEY"):
-        server.add_tool(extract_bitflip_info)
-        server.add_tool(generate_research_proposals)
-        server.add_tool(score_research_proposals)
-        server.add_tool(document_qa)
-        server.add_tool(review_pdf_paper)
-
-    if port is None:
-        port = int(os.environ.get("PORT", -1))
-        if port == -1:
-            port = find_free_port()
-    server.settings.port = port
-    server.settings.host = host
-    server.run(transport=transport)
-
-
-if __name__ == "__main__":
-    fire.Fire(run)