annas-mcp
MCP server and CLI that searches and downloads books and articles from Anna's Archive inside an agent
- 1,119 ★ on the repository
- Last commit
Extended access
Why this level
- Downloads files from the network and writes them to disk
- Downloads need an API key, keep it out of chats and repositories
Install
- Works in
Manual install
{
"mcpServers": {
"annas-mcp": {
"command": "/path/to/annas-mcp",
"args": ["mcp"],
"env": {
"ANNAS_SECRET_KEY": "<ваш ключ>",
"ANNAS_DOWNLOAD_PATH": "/path/to/downloads"
}
}
}
}The key and download path are only needed for downloads, search works without them.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Downloads files from the network and writes them to disk
- Downloads need an API key, keep it out of chats and repositories
This is third-party code. Review the repository files before installing.
What it does
The project offers two ways to work with Anna's Archive: as an MCP server for clients such as Claude Desktop, and as a plain command line tool. Searching books and articles by title, author or DOI works without a key. Downloading a file needs an API key, granted after a donation to the site. An optional mirror picker reads the public status page and selects a reachable mirror. It ships as a single Go binary installed from releases.
Who it is for. For people who look up open-access papers and books and want to fetch them through an agent.
Good fit when
- You need to find a book or paper by title, author or DOI
- You want to download items through an agent command instead of the site
- You need Anna's Archive access from Claude Desktop
Not a fit when
- You have no API key or donation but need downloads rather than search
- Handling copyrighted material conflicts with your rules or local law
Example request
Find the paper with DOI 10.1038/nature12345 and download it to my downloads folderMCP
- Transport
- stdio
- Authentication
- key is optional
Environment variables
ANNAS_SECRET_KEYsecret- Anna's Archive API key, required to download files
ANNAS_DOWNLOAD_PATH- Folder where downloaded files are saved
ANNAS_BASE_URL- Default mirror, otherwise annas-archive.gl
ANNAS_AUTO_BASE_URL- Set to true to auto-discover a reachable mirror
Limitations
Search is free, downloads require an API key and a donation. Anna's Archive mirrors change and can be unreachable, and access from some regions is not guaranteed. The repository states no license. Respecting copyright is the user's responsibility.
How to disable. Remove the annas-mcp entry from the MCP client config and delete the downloaded binary.
FAQ
Do I need a key to search?
No, searching books and papers works without a key. The API key is only needed to download files and is granted after a donation.
Can I use it without MCP?
Yes, the same binary works as a CLI: book-search, book-download, article-search and article-download.
How is annas-mcp different from searching for books in a browser?
The project works as an MCP server for clients like Claude Desktop and as an ordinary command line utility. Searching books and papers by title, author or DOI happens right from the agent.
Does annas-mcp need a key for search?
Search by title, author and DOI works without a key. Downloading files depends on the service settings and may need a key. The server connects to Claude Desktop, see the install block. Follow copyright laws in your country.
Discussion
No questions or reviews yet.
Related
MCP serversA local MCP server for arXiv literature work: section-level paper reads, BibTeX from metadata, topic watches
Academia MCP: scientific paper search
Academia MCP
An MCP server for scientific work: search arXiv and ACL Anthology, Semantic Scholar citations, PDF reading and LaTeX compilation
A CLI and MCP server for a research paper library: the agent searches, imports and reads papers and keeps Markdown notes in your vault
A Zotero plugin with a built-in MCP server: the agent searches the library, reads PDFs and notes, and works with annotations and metadata
MCP PDF for large documents: the agent searches by meaning and keyword across one file or a folder and reads only the pages, tables and scans it needs
MCP for PDF and ebook files: the agent finds books in a folder and reads EPUB and PDF by chapter and page, with contents and metadata as Markdown
README in short
The README covers install from releases, MCP setup for Claude Desktop and environment variables. Search works out of the box, downloads need an API key and a donation. A mirror section explains that ANNAS_AUTO_BASE_URL turns on automatic mirror discovery through the SLUM status page, otherwise ANNAS_BASE_URL is used. It lists an operations table for MCP and CLI and timeout options.