MCP Books runs on your own machine — the client starts it, so there is no endpoint to ping. 85 installs a week from npm. Last commit 15 Oct 2026.
Search the Internet Archive, the Library of Congress and data.bnf.fr at once, in one answer.
Today is the operative word: we check MCP Books every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-books -- npx -y mcp-books
{
"mcpServers": {
"mcp-books": {
"args": [
"-y",
"mcp-books"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-books]
command = "npx"
args = ["-y", "mcp-books"]
{
"mcpServers": {
"mcp-books": {
"args": [
"-y",
"mcp-books"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-books": {
"args": [
"-y",
"mcp-books"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
BOOKS_USER_AGENT (Identify your own client. The project's own identifier is appended, so an archive can always reach a human.), BOOKS_MIN_INTERVAL_MS (Widen the gap between two requests to one archive. Each archive keeps its own spacing when this is unset, and this can only make it wider.), BOOKS_TIMEOUT_MS (Deadline for one request to an archive, in milliseconds. Default 45000.), BOOKS_MAX_RETRIES (Retries on rate limiting and transient failures. Default 3.), BOOKS_CACHE_TTL_MS (In-memory cache lifetime, in milliseconds. Default 900000. Set 0 to turn it off.), BOOKS_CACHE_MAX_ENTRIES (In-memory cache size. Default 200.), BOOKS_LOG_LEVEL (silent, error, info or debug. Default error. Logs go to stderr.).
The author declared them in the registry entry; get the values from the project itself.
Search books and authors on the Internet Archive's Open Library
Search books and authors across Open Library, the Internet Archive open catalog.
Search inside scanned US newspapers and browse the Library of Congress catalogue. No API key.
Search the Library of Congress collections. No key required.
Internet Archive search, item metadata, and Wayback snapshots.
Search inside digitised books, browse the Internet Archive catalogue and read Wayback captures.
B2B company address data for the DACH region: search 6,400+ industry lists and get price quotes.
Search, save, tag, and summarize the links in your Link Crypt bookmark library.
Answers built from our own checks of this server.