academia-mcp 1.9.0__py3-none-any.whl → 1.9.1__py3-none-any.whl

academia_mcp/server.py

@@ -10,7 +10,12 @@ 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.s2 import (
+    s2_get_citations,
+    s2_get_references,
+    s2_corpus_id_from_arxiv_id,
+    s2_get_info,
+)
 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
@@ -75,6 +80,8 @@ def run(
     server.add_tool(arxiv_download)
     server.add_tool(s2_get_citations)
     server.add_tool(s2_get_references)
+    server.add_tool(s2_corpus_id_from_arxiv_id)
+    server.add_tool(s2_get_info)
     server.add_tool(hf_datasets_search)
     server.add_tool(anthology_search)
     server.add_tool(get_latex_template)

academia_mcp/tools/__init__.py

@@ -2,7 +2,7 @@ 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_get_references, s2_get_citations
+from .s2 import s2_get_references, s2_get_citations, s2_corpus_id_from_arxiv_id, s2_get_info
 from .document_qa import document_qa
 from .latex import (
     compile_latex,
@@ -21,6 +21,8 @@ __all__ = [
     "anthology_search",
     "s2_get_references",
     "s2_get_citations",
+    "s2_corpus_id_from_arxiv_id",
+    "s2_get_info",
     "hf_datasets_search",
     "document_qa",
     "compile_latex",

academia_mcp/tools/{s2_citations.py → s2.py}

@@ -126,3 +126,38 @@ def s2_get_references(
     entries = result["data"]
     total_count = len(result["data"]) + result["offset"]
     return _format_entries(entries, offset if offset else 0, total_count)
+
+
+def s2_corpus_id_from_arxiv_id(arxiv_id: str) -> int:
+    """
+    Get the S2 Corpus ID for a given arXiv ID.
+
+    Args:
+        arxiv_id: The ID of a given arXiv paper.
+    """
+    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_url = PAPER_URL_TEMPLATE.format(paper_id=f"arxiv:{arxiv_id}", fields="externalIds")
+    response = get_with_retries(paper_url)
+    result = response.json()
+    return int(result["externalIds"]["CorpusId"])
+
+
+def s2_get_info(arxiv_id: str) -> str:
+    """
+    Get the S2 info for a given arXiv ID.
+
+    Returns a JSON object serialized to a string. The structure is:
+    {"title": ..., "authors": ..., "externalIds": ..., "venue": ..., "citationCount": ..., "publicationDate": ...}
+    Use `json.loads` to deserialize the result if you want to get specific fields.
+
+    Args:
+        arxiv_id: The ID of a given arXiv paper.
+    """
+    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_url = PAPER_URL_TEMPLATE.format(paper_id=f"arxiv:{arxiv_id}", fields=FIELDS)
+    response = get_with_retries(paper_url)
+    return json.dumps(response.json(), ensure_ascii=False)

academia_mcp-1.9.1.dist-info/METADATA

@@ -0,0 +1,170 @@
+Metadata-Version: 2.4
+Name: academia-mcp
+Version: 1.9.1
+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>=1.10.1
+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: huggingface-hub>=0.32.4
+Requires-Dist: fire>=0.7.0
+Requires-Dist: openai>=1.97.1
+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
+
+[![PyPI](https://img.shields.io/pypi/v/academia-mcp?label=PyPI%20package)](https://pypi.org/project/academia-mcp/)
+[![CI](https://github.com/IlyaGusev/academia_mcp/actions/workflows/python.yml/badge.svg)](https://github.com/IlyaGusev/academia_mcp/actions/workflows/python.yml)
+[![License](https://img.shields.io/github/license/IlyaGusev/academia_mcp)](LICENSE)
+[![smithery badge](https://smithery.ai/badge/@IlyaGusev/academia_mcp)](https://smithery.ai/server/@IlyaGusev/academia_mcp)
+[![Verified on MseeP](https://mseep.ai/badge.svg)](https://mseep.ai/app/e818878b-c3a6-4b3d-a5b4-e54dcd1f1fed)
+
+MCP server with tools to search, fetch, analyze, and report on scientific papers and datasets.
+
+### Features
+- ArXiv search and download
+- ACL Anthology search
+- Hugging Face datasets search
+- Semantic Scholar citations and references
+- Web search via Exa, Brave, or Tavily
+- Web page crawler, LaTeX compilation, PDF reading
+- Optional LLM-powered tools for document QA and research proposal workflows
+
+### Requirements
+- Python 3.12+
+
+### Install
+- Using pip (end users):
+```bash
+pip3 install academia-mcp
+```
+
+- For development (uv + Makefile):
+```bash
+uv venv .venv
+make install
+```
+
+### Quickstart
+- Run over HTTP (default transport):
+```bash
+uv run -m academia_mcp --transport streamable-http
+```
+
+- Run over stdio (for local MCP clients like Claude Desktop):
+```bash
+python -m academia_mcp --transport stdio
+```
+
+Notes:
+- Transports: `stdio`, `sse`, `streamable-http`.
+- `host`/`port` are used for HTTP transports; ignored for `stdio`. Default port is `5056` (or `PORT`).
+
+### Claude Desktop config
+```json
+{
+  "mcpServers": {
+    "academia": {
+      "command": "python3",
+      "args": [
+        "-m",
+        "academia_mcp",
+        "--transport",
+        "stdio"
+      ]
+    }
+  }
+}
+```
+
+### Available tools (one-liners)
+- `arxiv_search`: Query arXiv with field-specific queries and filters.
+- `arxiv_download`: Fetch a paper by ID and convert to structured text (HTML/PDF modes).
+- `anthology_search`: Search ACL Anthology with fielded queries and optional date filtering.
+- `hf_datasets_search`: Find Hugging Face datasets with filters and sorting.
+- `s2_get_citations`: List papers citing a given arXiv paper (Semantic Scholar Graph).
+- `s2_get_references`: List papers referenced by a given arXiv paper.
+- `visit_webpage`: Fetch and normalize a web page.
+- `web_search`: Unified search wrapper; available when at least one of Exa/Brave/Tavily keys is set.
+- `exa_web_search`, `brave_web_search`, `tavily_web_search`: Provider-specific search.
+- `get_latex_templates_list`, `get_latex_template`: Enumerate and fetch built-in LaTeX templates.
+- `compile_latex`: Compile LaTeX to PDF in `WORKSPACE_DIR`.
+- `read_pdf`: Extract text per page from a PDF.
+- `download_pdf_paper`, `review_pdf_paper`: Download and optionally review PDFs (requires LLM + workspace).
+- `document_qa`: Answer questions over provided document chunks (requires LLM).
+- `extract_bitflip_info`, `generate_research_proposals`, `score_research_proposals`: Research proposal helpers (requires LLM).
+
+Availability notes:
+- Set `WORKSPACE_DIR` to enable `compile_latex`, `read_pdf`, `download_pdf_paper`, and `review_pdf_paper`.
+- Set `OPENROUTER_API_KEY` to enable LLM tools (`document_qa`, `review_pdf_paper`, and bitflip tools).
+- Set one or more of `EXA_API_KEY`, `BRAVE_API_KEY`, `TAVILY_API_KEY` to enable `web_search` and provider tools.
+
+### Environment variables
+Set as needed depending on which tools you use:
+
+- `OPENROUTER_API_KEY`: required for LLM-related tools.
+- `BASE_URL`: override OpenRouter base URL.
+- `DOCUMENT_QA_MODEL_NAME`: override default model for `document_qa`.
+- `BITFLIP_MODEL_NAME`: override default model for bitflip tools.
+- `TAVILY_API_KEY`: enables Tavily in `web_search`.
+- `EXA_API_KEY`: enables Exa in `web_search` and `visit_webpage`.
+- `BRAVE_API_KEY`: enables Brave in `web_search`.
+- `WORKSPACE_DIR`: directory for generated files (PDFs, temp artifacts).
+- `PORT`: HTTP port (default `5056`).
+
+You can put these in a `.env` file in the project root.
+
+### Docker
+Build the image:
+```bash
+docker build -t academia_mcp .
+```
+
+Run the server (HTTP):
+```bash
+docker run --rm -p 5056:5056 \
+  -e PORT=5056 \
+  -e OPENROUTER_API_KEY=your_key_here \
+  -e WORKSPACE_DIR=/workspace \
+  -v "$PWD/workdir:/workspace" \
+  academia_mcp
+```
+
+Or use existing image: `phoenix120/academia_mcp`
+
+### Examples
+- [Comprehensive report screencast (YouTube)](https://www.youtube.com/watch?v=4bweqQcN6w8)
+- [Single paper screencast (YouTube)](https://www.youtube.com/watch?v=IAAPMptJ5k8)
+
+### Makefile targets
+- `make install`: install the package in editable mode with uv
+- `make validate`: run black, flake8, and mypy (strict)
+- `make test`: run the test suite with pytest
+- `make publish`: build and publish using uv
+
+### LaTeX/PDF requirements
+Only needed for LaTeX/PDF tools. Ensure a LaTeX distribution is installed and `pdflatex` is on PATH, as well as `latexmk`. On Debian/Ubuntu:
+```bash
+sudo apt install texlive-latex-base texlive-fonts-recommended texlive-latex-extra texlive-science latexmk
+```

{academia_mcp-1.9.0.dist-info → academia_mcp-1.9.1.dist-info}/RECORD

@@ -4,12 +4,12 @@ academia_mcp/files.py,sha256=ynIt0XbU1Z7EPWkv_hVX0pGKsLlmjYv-MVJLOfi6yzs,817
 academia_mcp/llm.py,sha256=zpGkuJFf58Ofgys_fi28-47_wJ1a7sIs_yZvI1Si6z0,993
 academia_mcp/pdf.py,sha256=9PlXzHGhb6ay3ldbTdxCcTWvH4TkET3bnb64mgoh9i0,1273
 academia_mcp/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-academia_mcp/server.py,sha256=ufNqg_C75ziQFXSZY7rYc41XA6LUBEAmCrX0RyMopjk,4198
+academia_mcp/server.py,sha256=qg2Q7sIddx3HH83nks-dIkrHykVEtFxN5UAAVlj5OSI,4331
 academia_mcp/settings.py,sha256=vkhCrglL_OI1W0Me_1vS0WoQwDhpzj_XTfcuOylweYA,907
 academia_mcp/utils.py,sha256=P9U3RjYzcztE0KxXvJSy5wSBaUg2CM9tpByljYrsrl4,4607
 academia_mcp/latex_templates/agents4science_2025/agents4science_2025.sty,sha256=hGcEPCYBJS4vdhWvN_yEaJC4GvT_yDroI94CfY2Oguk,12268
 academia_mcp/latex_templates/agents4science_2025/agents4science_2025.tex,sha256=Tl1QkHXHRopw9VEfWrD3Layr5JP_0gIzVQjL4KXIWqc,15814
-academia_mcp/tools/__init__.py,sha256=Bf76VHYQtRKXsHukdwmxhDVcaVdtlsnMlHe4nxbcUMI,1253
+academia_mcp/tools/__init__.py,sha256=zaEPj0kUo9ng40wkJcrEijbvu2OoBQ0392OhqF6Q0Uo,1337
 academia_mcp/tools/anthology_search.py,sha256=rhFpJZqGLABgr0raDuH0CARBiAJNJtEI4dlMrKNHfDQ,7669
 academia_mcp/tools/arxiv_download.py,sha256=gBY0_Kz0yGtVkLMwn6GrAyfBjovZVgcSMuyy67p65Cw,10474
 academia_mcp/tools/arxiv_search.py,sha256=pzM18qrF3QL03A53w003kE7hQi3s3QKtjgw0m7K88UY,8355
@@ -19,12 +19,12 @@ academia_mcp/tools/hf_datasets_search.py,sha256=KiBkqT4rXjEN4oc1AWZOPnqN_Go90TQo
 academia_mcp/tools/latex.py,sha256=B1Leqt1FHY6H3DlUgeYse4LMFpf4-K1FQViXl5MKk8A,6144
 academia_mcp/tools/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 academia_mcp/tools/review.py,sha256=Va0lFJJKuk-NvWhKS3UZ-Dnuk7CyuDQ4S1nd70D-ffE,11117
-academia_mcp/tools/s2_citations.py,sha256=XZ3a4rsovAiI_D_kIy0GddRHSjpC5Fa_CS8dmB9Qftg,4902
+academia_mcp/tools/s2.py,sha256=QX7-pbetab3Xt_1tvVPU6o5D_NAe9y6jcTGRBK1vwtY,6200
 academia_mcp/tools/visit_webpage.py,sha256=uEqZIkMqscZG58Rx2wd6L_OQkGxo5SrzCkoUB55HhC0,2018
 academia_mcp/tools/web_search.py,sha256=kj3BrPdTVfyTjZ_9Jl2n3YUGzcRZk8diQs6cVSVmPrQ,6293
-academia_mcp-1.9.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-academia_mcp-1.9.0.dist-info/METADATA,sha256=GQCmidDARqWtdZuOFww8Sdg5CRCGGOIooeHlS6TIlJ8,3754
-academia_mcp-1.9.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-academia_mcp-1.9.0.dist-info/entry_points.txt,sha256=gxkiKJ74w2FwJpSECpjA3XtCfI5ZfrM6N8cqnwsq4yY,51
-academia_mcp-1.9.0.dist-info/top_level.txt,sha256=CzGpRFsRRJRqWEb1e3SUlcfGqRzOxevZGaJWrtGF8W0,13
-academia_mcp-1.9.0.dist-info/RECORD,,
+academia_mcp-1.9.1.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+academia_mcp-1.9.1.dist-info/METADATA,sha256=_FtfoLH4Nnv7D5oLT33HKW6UzMtUxQk3IR4Wp4O1jWw,6310
+academia_mcp-1.9.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+academia_mcp-1.9.1.dist-info/entry_points.txt,sha256=gxkiKJ74w2FwJpSECpjA3XtCfI5ZfrM6N8cqnwsq4yY,51
+academia_mcp-1.9.1.dist-info/top_level.txt,sha256=CzGpRFsRRJRqWEb1e3SUlcfGqRzOxevZGaJWrtGF8W0,13
+academia_mcp-1.9.1.dist-info/RECORD,,

academia_mcp-1.9.0.dist-info/METADATA

@@ -1,122 +0,0 @@
-Metadata-Version: 2.4
-Name: academia-mcp
-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
-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>=1.10.1
-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: huggingface-hub>=0.32.4
-Requires-Dist: fire>=0.7.0
-Requires-Dist: openai>=1.97.1
-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
-
-[![PyPI](https://img.shields.io/pypi/v/codearkt?label=PyPI%20package)](https://pypi.org/project/academia-mcp/)
-[![CI](https://github.com/IlyaGusev/academia_mcp/actions/workflows/python.yml/badge.svg)](https://github.com/IlyaGusev/academia_mcp/actions/workflows/python.yml)
-[![License](https://img.shields.io/github/license/IlyaGusev/academia_mcp)](LICENSE)
-[![smithery badge](https://smithery.ai/badge/@IlyaGusev/academia_mcp)](https://smithery.ai/server/@IlyaGusev/academia_mcp)
-
-A collection of MCP tools related to the search of scientific papers:
-- ArXiv search and download
-- ACL Anthology search
-- HuggingFact datasets search
-- Semantic Scholar citation graphs
-- Web search: Exa/Brave/Tavily
-- Page crawler
-
-## Install
-
-- Using pip (end users):
-```
-pip3 install academia-mcp
-```
-
-- For development (uv + Makefile):
-```
-uv venv .venv
-make install
-```
-
-## Examples
-Comprehensive report screencast: https://www.youtube.com/watch?v=4bweqQcN6w8
-
-Single paper screencast: https://www.youtube.com/watch?v=IAAPMptJ5k8
-
-
-## Claude Desktop config
-```
-{
-  "mcpServers": {
-    "academia": {
-      "command": "python3",
-      "args": [
-        "-m",
-        "academia_mcp",
-        "--transport",
-        "stdio"
-      ]
-    }
-  }
-}
-```
-
-## Running the server (CLI)
-
-```
-uv run -m academia_mcp --transport streamable-http
-```
-
-Notes:
-- Transports supported: `stdio`, `sse`, `streamable-http`.
-- Host/port are used for HTTP transports; for `stdio` they are ignored.
-
-## Makefile targets
-
-- `make install`: install the package in editable mode with uv.
-- `make validate`: run black, flake8, and mypy (strict).
-- `make test`: run the test suite with pytest.
-- `make publish`: build and publish using uv.
-
-## Environment variables
-
-Set as needed depending on which tools you use:
-
-- `TAVILY_API_KEY`: enables Tavily in `web_search`.
-- `EXA_API_KEY`: enables Exa in `web_search` and `visit_webpage`.
-- `BRAVE_API_KEY`: enables Brave in `web_search`.
-- `OPENROUTER_API_KEY`: required for `document_qa`.
-- `BASE_URL`: override OpenRouter base URL for `document_qa` and bitflip tools.
-- `DOCUMENT_QA_MODEL_NAME`: override default model for `document_qa`.
-- `BITFLIP_MODEL_NAME`: override default model for bitflip tools.
-- `WORKSPACE_DIR`: directory for generated files (PDFs, temp artifacts).
-
-## md_to_pdf requirements
-
-The `md_to_pdf` tool invokes `pdflatex`. Ensure a LaTeX distribution is installed and `pdflatex` is on PATH. On Debian/Ubuntu:
-
-```
-sudo apt install texlive-latex-base texlive-fonts-recommended texlive-latex-extra texlive-science
-```