Connect Books & Papers and your agent gets 4 tools, among them download, get_details, read. It answers at https://mcp.jmrp.io/libgen over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 22 October 2026, succeeded.
Federated search of books and papers, BibTeX/RIS citations, open-access retrieval and reading.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
download | Resolve a downloadable copy of a book or article. Provide md5 (book), isbn (book), doi (article); at least one is required. This server runs remotely and cannot write to your disk: download ALWAYS returns a direct link (a resource_link) to Inputs: md5, doi, isbn, path, filename, source |
get_details | Full metadata for one bibliographic record — identifiers, DOI, cover, related edition — plus ready-to-paste BibTeX and RIS exports in its citations field. Use it whenever a citation is requested. Look up by exactly one of md5, edition/file Inputs: md5, id, doi, object, enrich |
read | Read a book or paper's text in chunks without downloading the whole file. Identify it by md5, doi, or absolute local path (local server only); PDFs paginate by page, EPUB/TXT by character offset. While has_more, re-call with the cursor. fin Inputs: md5, doi, source, start_page, max_pages, offset |
search | Federated search for books, papers, comics, magazines and standards, returning per-result metadata, md5 and download links. Beyond the primary catalog it also reaches Anna's Archive and the keyless open-access providers, returned as a separ Inputs: query, topics, search_in, results_per_page, page, order |
Every block below points at https://mcp.jmrp.io/libgen. Pick your client and copy.
claude mcp add --transport http books-papers https://mcp.jmrp.io/libgen
{
"mcpServers": {
"books-papers": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.jmrp.io/libgen"]
}
}
}{
"mcpServers": {
"books-papers": {
"url": "https://mcp.jmrp.io/libgen"
}
}
}{
"servers": {
"books-papers": {
"type": "http",
"url": "https://mcp.jmrp.io/libgen"
}
}
}{
"context_servers": {
"books-papers": {
"url": "https://mcp.jmrp.io/libgen"
}
}
}{
"mcpServers": {
"books-papers": {
"serverUrl": "https://mcp.jmrp.io/libgen"
}
}
}{
"mcpServers": {
"books-papers": {
"url": "https://mcp.jmrp.io/libgen"
}
}
}name: Books & Papers
version: 0.0.1
schema: v1
mcpServers:
- name: Books & Papers
type: streamable-http
url: https://mcp.jmrp.io/libgen{
"mcpServers": {
"books-papers": {
"httpUrl": "https://mcp.jmrp.io/libgen"
}
}
}{
"mcpServers": {
"books-papers": {
"type": "http",
"url": "https://mcp.jmrp.io/libgen"
}
}
}{
"mcpServers": {
"books-papers": {
"url": "https://mcp.jmrp.io/libgen"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.jmrp.io%2Flibgen&type=streamable_http&id=books-papers&name=Books%20%26%20Papers
It answered our last check on 22 October 2026 in 279 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
4, as returned by the server's own tools/list on 14 September 2026: download, get_details, read, search.
It answered our last check on 22 October 2026 in 279 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.jmrp.io/libgen. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.jmrplens. Endpoint host: mcp.jmrp.io. ARD identifier: urn:air:io.github.jmrplens:mcp:libgen-mcp.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.