Library of Alexandria
Classic books in 25 languages: search, print editions, the free shelf. Read-only, no sign-in.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
claude mcp add --transport http library-of-alexandria 'https://mcp.libraryofalexandria.com/mcp'{
"mcpServers": {
"library-of-alexandria": {
"type": "http",
"url": "https://mcp.libraryofalexandria.com/mcp"
}
}
}Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Contents
Library of Alexandria for developers
The library's catalogue, its free shelf and its print editions, as one small set of read-only tools that any program, assistant or model can call. There is no key and nothing to sign up for. The tools never sign anyone in, take a payment or change anything; every title they return carries the address of its page on libraryofalexandria.com, where a person reads, listens, prints or starts.
Three doors lead to the same eight tools:
| Door | Address | For | |||||
|---|---|---|---|---|---|---|---|
| MCP (Streamable HTTP) | https://mcp.libraryofalexandria.com/mcp | Claude, ChatGPT, Gemini, Grok, Copilot, Perplexity, Le Chat, LM Studio, Open WebUI, Cursor, VS Code, Goose and every other MCP client | |||||
| REST + OpenAPI 3.1 | POST https://api.libraryofalexandria.com/v1/<tool> and GET .../v1/openapi.json | scripts, automation tools (n8n, Zapier, Make, Dify, Flowise), Open WebUI tool servers, Copilot Studio | |||||
| Tool files for model makers | `GET .../v1/tools?format=openai | openai-chat | anthropic | gemini | ollama | mcp` | any program that passes tool definitions to a model |
The eight tools
| Tool | What it does |
|---|---|
search_books | find titles by words from a title, an author or a topic, in any language of the catalogue |
get_book | the facts of one title: author, original title, cover, print editions, its page in each language |
get_summary | the first key idea of the 15-minute summary of one title in full, and the headings of the others (part chooses one) |
get_sample | the free opening of one title, in pages of at most 400 words (page chooses one) |
list_free_shelf | the titles on the free shelf, by language and subject |
read_free_chapter | one chapter of a free-shelf title, in pages of at most 400 words |
get_print_options | the print editions of one title (standard and large print; paperback or hardcover) with the list price in US dollars |
get_publisher_info | who publishes the library, the languages, the terms and privacy pages |
A summary, a sample page or a free-shelf chapter that is not open yet (a title, a language, or all texts before they go online) answers plainly that it "opens here soon"; the tools then fill in without any change on your side. The text tools count the words they hand out for each client (72,000 a day and 48,000 an hour) and show what is left in budget.
Try it in a minute
curl -s https://api.libraryofalexandria.com/v1/search_books \
-H 'content-type: application/json' -d '{"query":"moby dick","limit":3}'The answer is {"ok": true, "data": {...}, "source": "Library of Alexandria, libraryofalexandria.com"}. A problem comes back as application/problem+json (RFC 9457) with a stable code; see openapi/loa-api.openapi.json.
What is in this folder
| Path | What |
|---|---|
openapi/loa-api.openapi.json | the OpenAPI 3.1 file (also served live at /v1/openapi.json) |
function-tools/*.json | the eight tools in the shapes of OpenAI (Responses and Chat Completions), Anthropic, Gemini, Ollama and MCP |
cli/loa.mjs | the command line loa (Node 18 or newer, no dependencies) |
sdk/typescript/loa.mjs, loa.d.ts | the JavaScript and TypeScript client (no dependencies; browsers, Node, Deno, Bun, Workers) |
sdk/python/loa_library.py | the Python client (standard library only) |
sdk/python/loa_tools.py | one plain Python function per tool, for Ollama and any framework that builds tool schemas from type hints |
mcp-bridge/loa-mcp.mjs | a stdio bridge for MCP clients that cannot reach a remote server |
quickstarts/ | how to connect LM Studio, Open WebUI, Ollama, Goose, Claude, ChatGPT, Cursor, VS Code, LangChain and the OpenAI Agents SDK |
AGENTS.md, SKILL.md | instructions for coding agents and for assistants that help a person with the library |
tests/ | the tests of this kit (node --test tests/*.test.mjs and python3 tests/test_python.py) |
The generated files (openapi/, function-tools/) are made from the service's own code; a test in the service fails when they are out of date.
Rules of the library, for everyone who quotes it
- Say what the answer says; use the
urlof a title as given; never invent a price or an offer. - The library is not the ancient library of Alexandria and not the Bibliotheca Alexandrina.
- Payments and sign-up happen on libraryofalexandria.com only; a tool can hand over a link, never take a payment.
- Please keep to a few requests a second and send a
User-Agentthat names your program.
Versions
The API version is a date, sent back in the LOA-Version header (2026-10-25). Changes are announced on the developer page.
Licence
MIT, see LICENSE. The library's tools return catalogue facts, short summaries and free parts as the service allows; the licence covers this code and these documents, not the books.
Registry entry
The description of the server for the official MCP Registry is in server.json.
Frequently asked questions
What is Library of Alexandria?
Classic books in 25 languages: search, print editions, the free shelf. Read-only, no sign-in.
How do I install Library of Alexandria?
It runs as a remote server. In Claude Code: claude mcp add --transport http library-of-alexandria 'https://mcp.libraryofalexandria.com/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.
Does Library of Alexandria need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Is Library of Alexandria open source?
Yes. Its code is on GitHub under the MIT license.
Who maintains Library of Alexandria?
It is published by ltvspot. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.