litdb CLI
litdb keeps your scientific literature in a local database with semantic search and gives an agent a skill and an MCP server
- 86 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Indexes your files and calls OpenAlex and CrossRef over the network
- The MCP server exposes the contents of your paper database to the agent for reading
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add cli/litdbDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Indexes your files and calls OpenAlex and CrossRef over the network
- The MCP server exposes the contents of your paper database to the agent for reading
This is third-party code. Review the repository files before installing.
What it does
litdb is a tool for collecting and using a collection of scientific papers: you add papers, search with natural language queries, follow new articles and read older ones. Search uses SentenceTransformer models, data comes from OpenAlex, CrossRef and local files, and you can chat with a model through ollama. For agents such as Claude Code, VS Code with GitHub Copilot, Cursor, Codex, OpenCode and Gemini CLI there are two artifacts. The `skills/litdb/SKILL.md` skill teaches an agent to work with the CLI: add papers, search, filter, tag and export BibTeX. The `litdb_mcp` MCP server gives the agent read-only tools: `vsearch`, `fulltext_search`, `find_similar`, `openalex`, `get_source_details`, `get_citation`, `get_bibtex`, `list_tags` and `get_tagged_articles`. Version 2.1.8 added `fromtext` to extract references from pasted text, `summary` for digests of new articles, `extract` for PDF tables and `schema` for structured data from documents. Configuration lives in `litdb.toml`.
Who it is for. Researchers who accumulate papers and want to search them in natural language and give the database to an agent for reading and citing.
Good fit when
- The database has hundreds of papers on a topic and you need ones similar to a specific work
- An agent should pick BibTeX and references from your collection without outside services
- Records should be built from a pasted reference list with CrossRef matching
- New articles on a topic should be skimmed as a short digest
Not a fit when
- You need only a reference manager without semantic search: the project pulls many ML dependencies
- Papers live in a cloud manager and you do not want a local copy
- You need OpenAlex premium filters without a paid key
Example request
Find papers in my litdb database similar to this work and export BibTeX for the three closestLimitations
- The project has many ML dependencies and version conflicts are common: the author advises installing through `uv`.
- Before use a `litdb.toml` file is created with a SentenceTransformer model, vector size and chunking settings.
- The `update-filters` feature needs a premium OpenAlex key.
- The MCP server gives read-only tools, and adding papers goes through the CLI.
- Some features such as `fromtext` rely on model parsing and CrossRef, so they need network access.
How to disable. Remove the package with `uv tool uninstall litdb` or `pip uninstall litdb` and remove the skill and the MCP entry from agent settings.
FAQ
Which tools does the litdb MCP server give?
Nine read-only tools: vector and full text search, similar papers, OpenAlex queries, citations, BibTeX and tags.
How do I install litdb without dependency conflicts?
Through `uv`: `uv venv --python 3.13` then `uv pip install litdb`, or `uv tool install litdb` to put the commands on PATH.
Which agents does it work with?
The skill and MCP fit Claude Code, VS Code with GitHub Copilot, Cursor, Codex, OpenCode and Gemini CLI; knowhow installs them most easily.
Where do papers come from?
From OpenAlex, CrossRef and local files, and they are then indexed locally.
What does the fromtext command do?
It extracts references from pasted text using model parsing and CrossRef matching and adds them to the database.
Discussion
No questions or reviews yet.
Related
CLI toolsA local MCP server for arXiv literature work: section-level paper reads, BibTeX from metadata, topic watches
A skill that searches five open databases for papers and builds an offline report with relevance, BibTeX and search strategies.
Python CLI that compiles a book into an installable Agent Skill: a knowledge pack or a behavior skill with verbatim quote checks
The Zotero Literature Visualizer skill finds papers, organizes a Zotero library and builds an interactive literature dashboard.
BibTeX verification against Crossref, OpenAlex, PubMed and arXiv: a CLI, Python API and MCP server to flag wrong references
A Claude Code skill for scientific literature reviews: an interview, Scopus and OpenAlex search, DOI checks and a final docx file
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| litdb (this card) | no | 86 | ||
| Zotero Research Assistant Skill | no | 98 | works with a Zotero library through its own CLI, while litdb keeps its own database with semantic search | |
| zotero-mcp: an MCP server for your Zotero library | no | key is optional | 162 | an MCP exposing a Zotero library, while litdb keeps a local database with vectors and OpenAlex |
README in short
The README explains the literature database idea, lists video tutorials, install through `pip` and `uv`, version 2.1.8 additions and `litdb.toml` setup. A separate section covers the skill and MCP server for agents and install through knowhow.