pubmed-stream: PubMed search and PubMed Central full-text download, for researchers and their AI assistants

pubmed-stream is an open-source Python library and command-line tool that takes a PubMed search to a knowledge graph of the literature. It is built on NCBI's official E-utilities API, works from the command line or Python, and needs nothing beyond requests. AI assistants use it too: it is a plugin for Claude Code and Codex, and a PubMed MCP server for them and Gemini CLI, so you can ask a research question in plain English and get an answer that cites only papers the assistant downloaded and read.

With it you can:

• Search PubMed and PubMed Central (PMC) with field tags and MeSH (Medical Subject Headings), and see how many papers a search finds before downloading anything (section 2)
• Bulk-download full-text articles from PubMed Central as JSON, with metadata, references and text or JATS XML, and the PubMed abstracts of articles without free full text (section 1)
• Export citations as BibTeX or RIS for Zotero, EndNote and Mendeley (section 1)
• Find the papers that cite a paper, the papers it cites and the papers PubMed rates as similar, with retracted papers, reviews and NIH funding flagged (section 3)
• Build a knowledge graph of a study's literature in Obsidian, one Markdown note per paper and MeSH concept, linked by citations, similarity and topics (section 4)
• Give AI assistants PubMed tools through the MCP server or the plugin, and summarize abstracts with a local LLM through Ollama, so nothing leaves your computer (section 5)
• Measure the impact of a retracted paper through the papers citing it and the papers citing those (tutorial 8)

Documentation: melhzy.github.io/pubmed-stream, the tutorials, guides and reference in one searchable website, with every notebook shown with its results.

A study made with it: the Aβ*56 retraction impact page, how a retracted Alzheimer's paper spread through the literature and how much of it language models learned, as an interactive page where every number comes from the study's files; see Studies.

New to programming? Start with tutorial 0, which takes a research question to a map of its literature in an afternoon. Click Open in Colab to run it in your web browser, with nothing to install; you only type your question into one settings cell.

flowchart LR
    S["PubMed searches"] -->|"download"| D["Full-text articles<br/>metadata, references, text"]
    K["Key papers"] -->|"neighborhood"| N["Similar, citing and cited papers<br/>flagged reviews, retractions, NIH funding"]
    D --> G["Knowledge graph<br/>kg_topic, an Obsidian vault"]
    N --> G
    G --> O["Explore, write, refresh"]

Contents

• Quick start
• Tutorials
• Studies
• Installation and configuration
• 1. Download full-text articles from PubMed Central
• 2. Write PubMed searches that find the right papers
• 3. Map the evidence around a paper: citing, cited and similar articles
• 4. Build the knowledge graph of a study in Obsidian
• 5. Use it with AI assistants (MCP server and plugin), local models and Obsidian
• Python API for PubMed and NCBI E-utilities
• Troubleshooting
• How it works
• Contributing
• FAQ
• Citation, acknowledgments and license

This is the beginning of the README. Read the rest at the original. Read the full README ↗