MCP App Store
by KeenEthics
Paper Nexus icon

Paper Nexus MCP Server for Claude and ChatGPT

By Paper Nexus

Overview

Paper Nexus maps the scientific literature by its citations, across the scholarly works in OpenAlex and Semantic Scholar. Connect it to Claude to find a paper and the work around it, without leaving the conversation. Ask for papers related to one paper or several. Related means connected in the citation network (cited alongside, citing the same work), not merely similar wording, so it surfaces the papers a field builds on even when they use different terms. Give it several papers and the work linked to more than one of them comes first. Each recommendation says why it was picked: which of your papers it is linked to, whether it cites them or they cite it, and how many co-citations and shared references connect them. Every paper links to its page on papernex.us, and every set of recommendations comes with a link that opens the whole citation graph there. Find papers by title, DOI, or a link to arXiv, PubMed, doi.org or a publisher's page. Read a paper's details and its most-cited references, see the papers that cite it, and, if you allow it, work from the collections in your Paper Nexus library. Sign in with a free Paper Nexus account: no API key, 10 recommendation or citing-paper calls a week and 100 lookups a day. Premium raises that to 200 calls a day, combines up to 10 papers per request, and adds filters by year, citation count, author, venue, title words, citing or cited papers, open access and document type. All tools are read-only. Paper Nexus never changes your library or anything else on your behalf.

How to connect

  1. Claude: Open the Paper Nexus listing in the Claude connectors directory and choose Connect. Claude listing Paper Nexus exposes 9 tools here.
  2. ChatGPT: Open the Paper Nexus listing in the ChatGPT app directory and choose Connect. ChatGPT listing Paper Nexus exposes 11 tools here.

Tools

export_citations

ChatGPT
Cite papers in a reference manager or a bibliography: the papers as BibTeX, RIS (for Zotero, Mendeley or EndNote) or CSL-JSON (for Zotero, pandoc or citeproc), the same entries Paper Nexus's own export gives. Pass up to 50 Paper Nexus ids or papernex.us/paper/<id> links, or DOIs, arXiv ids, PMIDs, PMCIDs or OpenAlex ids, as papers; each paper counts as one lookup. Each entry holds what Paper Nexus has: title, authors (it keeps the first five, so a longer list is cut), year, venue, volume, issue and pages where known, DOI and other ids, and links. Nothing missing is filled in, so check the entries before a manuscript is submitted. content is the whole file, in the order given.

get_citation_edges

ChatGPT
How a set of papers connect: which of them cite which, such as among related papers found earlier or a reading list. Pass 2 to 100 Paper Nexus ids or papernex.us/paper/<id> links, or DOIs, arXiv ids, PMIDs, PMCIDs or OpenAlex ids, as papers; each paper counts as one lookup. It returns only the citations between the papers given, each as citing and cited ids, with how many of the others each paper cites and is cited by, and the papers linked to none of them. The links come from reference lists (OpenAlex and Semantic Scholar): a link missing is not proof that one paper does not cite the other, and a citation alone does not show that one paper builds on the other. Pass fields to get only the details of each paper you need.

get_paper

ChatGPT
One paper's details: its authors (Paper Nexus keeps the first five), venue, type, DOI, arXiv id, citation and reference counts, and its most-cited references. Pass a Paper Nexus id or a papernex.us/paper/<id> link. Pass fields to get only the details of each reference you need.

get_usage

ChatGPT
How many calls this account has left. recommend_papers and list_citing_papers each spend one of the allowance; a call that fails or finds nothing is not counted. The other tools share a larger daily limit of lookups, and every tool a limit of calls a minute. Each window starts at its first call, not at midnight, so the two end at different times. Call it before a task that needs many calls, to plan within them.

list_citing_papers

ChatGPT
The papers that cite one paper, newest first, earliest first, or most cited first, optionally within a span of years. Pass a Paper Nexus id or a papernex.us/paper/<id> link. Page through with offset; next_offset is null on the last page. Pass fields to get only the details of each paper you need. With filters, only the citing papers that pass them are listed, in the same order. Most cited first ranks by citations alone, so it is led by widely cited papers that cite this one in passing. For the citing papers closest to it, call recommend_papers with it as the origin and filters.cites set to it instead; add year_min for recent work.

list_library

ChatGPT
The user's own Paper Nexus library: with no collection, its collections and the first papers; with a collection (its name, path such as "Thesis / Methods", or id), the papers directly in it. Pass the paper ids to recommend_papers to explore around them. Page through with cursor; next_cursor is null on the last page. Pass fields to get only the details of each paper you need.

list_references

ChatGPT
What a paper builds on: the papers it cites that are in Paper Nexus, most cited first, newest first or earliest first, optionally within a span of years. Pass a Paper Nexus id or papernex.us/paper/<id> link, or a DOI, arXiv id, PMID, PMCID or OpenAlex id. Paper Nexus stores up to 600 references a paper; for a paper with more it holds an arbitrary 600, and complete is false. Page through with offset; next_offset is null on the last page. Pass fields to get only the details of each paper you need. With filters, only the references that pass them are listed, in the same order. Most cited first ranks by citations alone, so it is led by widely cited papers this one may cite in passing. For the references closest to its own work, call recommend_papers with it as the origin and filters.cited_by set to it instead.

recommend_papers

ChatGPT
Papers related to one or more origin papers, found through their citation network (co-citation and bibliographic coupling). Pass Paper Nexus ids from search_papers, or papernex.us/paper/<id> links. Several origins merge their related papers, with papers related to more than one of them first; origins from unrelated fields give a mix of each field's papers, not papers bridging them. Results are listed most related first: the order weighs how strongly each paper is linked to the origins (for well-connected origins, over a sample of their citers and references) and, without filters, also damps very highly cited papers and lifts recent ones. It orders this one list; it is not a probability of relevance or a measure of scientific importance. Each paper's evidence gives the citation links behind it, with link_counts saying how many co-citations and shared references link it to each origin, out of what each origin's sampled says was read: weigh a paper held up by few of them accordingly. graph_url opens the whole graph in Paper Nexus, which can hold more papers than limit. Pass fields to get only the details of each paper you need. With filters, every related paper passes them, best match first; years are the only date precision. To keep to papers linked to every origin, pass the origins as filters.cites with cites_match "all" (papers citing all of them), or narrow by topic with filters.title.

search_papers

ChatGPT
Find scientific papers by title and get their Paper Nexus ids, which recommend_papers takes. The query can also be a DOI or a link to a paper (doi.org, arXiv, PubMed, publisher pages). Returns up to limit matches, best first. Pass fields to get only the details of each paper you need.

submit_feedback

ChatGPT
Send the Paper Nexus team a short note about this service. Reports on its data are the most useful: a title, author list, year, venue, DOI or link that is wrong, a record that is really a different paper, citations or references that look off, or a paper, field or source the user needed and Paper Nexus doesn't have. Errors, timeouts, confusing tool descriptions or results, and features the user wished for are welcome too. Send one when the user asks to, or when you notice a problem with a Paper Nexus result, and tell the user what you sent. Say what you expected and what came back, and pass the papers it is about (Paper Nexus ids, links or DOIs) in papers. Leave out personal details, and the user's own text beyond what the report needs. A note changes no result now and gets no reply in this conversation; an account may send 10 a day.

verify_references

ChatGPT
Check a reference list or a bibliography: is each reference a real paper, the one it names, and where do its title, year, first author and DOI differ from Paper Nexus's record of it? Use it before relying on references an assistant wrote, or to check a manuscript's. Pass up to 50 references as references, each as written (a formatted reference in any style, a DOI, an arXiv, PubMed or publisher link, or a title) or as {title, authors, year, doi}; each counts as one lookup. Each comes back as found (the paper it names), conflict (its parts name different papers: a DOI or other identifier whose paper has another title, or a title whose paper has none of the authors given, the usual signs of a made-up or garbled reference), not_found, or not_checked, with what was read from it, so a misread one can be passed again as fields. A paper matched comes with the fields that agree, the differences (each with what Paper Nexus records), and notes on differences that are usually no error, such as a year apart for a preprint and its published version. Paper Nexus's record can be wrong too, so a difference is a field to check at the publisher, not proof the reference is wrong. not_found means not in Paper Nexus, which holds papers with citation data, not every publication: it is not proof that a reference was made up. Volume, issue and pages are not checked.

export_citations

Claude

get_paper

Claude

get_usage

Claude

list_citing_papers

Claude

list_library

Claude

list_references

Claude

recommend_papers

Claude

search_papers

Claude

verify_references

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/paper-nexus"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/paper-nexus)