Skip to main content

Academic literature search and citation workflows for PubMed, CrossRef, and arXiv

Project description

Nature Academic Search

CI PyPI Python

面向 Codex 和 Claude Code 的学术检索技能与 MCP 服务。统一搜索 PubMed、 CrossRef 和 arXiv,解析 DOI/PMID/arXiv ID,构建 MeSH 检索式,并导出 RIS、BibTeX、NBIB 或 ENW。

主要能力

  • 多源并发检索,按 DOI、PMID、arXiv ID、标题与年份去重
  • 保留来源追踪和单数据源失败信息
  • DOI、PMID、arXiv ID 自动识别与元数据核验
  • APA、Nature、IEEE、Vancouver 等引用格式
  • PubMed MeSH 词表查询
  • Codex 与 Claude Code 插件和安装器

PyPI 安装

推荐使用隔离工具环境:

uv tool install nature-academic-search
nature-academic-search install --client both --email researcher@example.com

也可使用 pipx install nature-academic-search。不要使用全局 pip install

从仓库安装并保留旧命令兼容:

bash install.sh researcher@example.com

插件安装

Codex:

codex plugin marketplace add wp-a/nature-academic-search
codex plugin add nature-academic-search@wp-a-academic-tools

Claude Code:

claude plugin marketplace add wp-a/nature-academic-search
claude plugin install nature-academic-search@wp-a-academic-tools

插件通过 uvx 启动固定版本的 PyPI MCP 服务。启动客户端前设置 PUBMED_EMAILNCBI_API_KEY 可选。

export PUBMED_EMAIL=researcher@example.com
export NCBI_API_KEY=optional-key

详见 安装说明

CLI

nature-academic-search --help
nature-academic-search serve
nature-academic-search preflight
nature-academic-search citation --pmid 28344011 --format ris
nature-academic-search citation --input refs.txt --format bib --output references/

MCP 保留四个稳定工具名:

Tool Purpose
search_papers Search one or more sources and deduplicate results
get_paper_by_id Resolve DOI, PMID, or arXiv metadata
get_citation Format one verified citation
lookup_mesh Find PubMed MeSH descriptors

开发

python -m pip install -e ".[test]"
python -m pytest
python -m pytest mcp-server/tests
python -m build
twine check dist/*

发布与维护流程见 维护手册

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nature_academic_search-0.1.0.tar.gz (67.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

nature_academic_search-0.1.0-py3-none-any.whl (38.8 kB view details)

Uploaded Python 3

File details

Details for the file nature_academic_search-0.1.0.tar.gz.

File metadata

  • Download URL: nature_academic_search-0.1.0.tar.gz
  • Upload date:
  • Size: 67.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for nature_academic_search-0.1.0.tar.gz
Algorithm Hash digest
SHA256 751d1491a5b79a8d09dfde3b15393ba6227c5b9f8a9ed0f8f08b9aabe2039b2c
MD5 ce6973129c10c0734b0b0905c53da3a6
BLAKE2b-256 ca9e493cab352fe74f7687393cc2c88cdc5c61e9f5f6e06c57c10970e84770c3

See more details on using hashes here.

Provenance

The following attestation bundles were made for nature_academic_search-0.1.0.tar.gz:

Publisher: publish.yml on wp-a/nature-academic-search

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file nature_academic_search-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for nature_academic_search-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 7e36c36a9f8c266cd96a03f094ef93c745ce2fec18a3d106169a341368192353
MD5 7aaac9dcebe4a415f4ba2a6be739fdb8
BLAKE2b-256 5406570022303e77a6a4fdaf406e1f413c69a000e47454cb377ddc29261b038e

See more details on using hashes here.

Provenance

The following attestation bundles were made for nature_academic_search-0.1.0-py3-none-any.whl:

Publisher: publish.yml on wp-a/nature-academic-search

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page