A side-by-side look at the Lune Research and Paperswithcode MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Lune Research for research work as a local process; choose Paperswithcode for research as a local process. You can also run both side by side in one mcpServers block.
LUNE_API_KEY.search_papers, search_papers_many, search_related_papers.search_papers, trending_papers, get_paper.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Research | Research |
| Quality signal | 57/100 · Good | 53/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | LUNE_API_KEY | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 4 | 0 |
| Directory activity | 0 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 12 | 4 |
| Full listing | View Lune Research | View Paperswithcode |
search_papersHybrid vector + BM25 search over the corpussearch_papers_manyMany query variants in one call, merged by reciprocal rank fusionsearch_related_papersThe nearest neighbors of a paper you already havelist_conferencesIndexed venues, optionally filtered by categoryget_conference_papersOne venue's papers, paginatedget_paper_fulltextParsed full text, as markdown or JSONget_paper_citationsThe citation graph, in either directionextract_from_papersPull the same structured fields out of a set of papersverify_claimsCheck each claim against the corpus, with a verbatim quote when one existsgather_evidenceJudge whether the evidence is sufficient yet, and name what is missingsearch_research_guidanceThe curated methodology and reproducibility corpusget_research_guidance_docThe full text of one guidance documentsearch_papersSearch machine-learning / AI research papers (via Hugging Face Papers, the successor to Papers with Code). Returns arXiv id, title, authors, community upvotes, and a linked GitHub repo when available. Use for "papers on <topic>", "recent ML research about X".trending_papersToday's trending ML/AI papers (or a given day's), ranked by community upvotes, via Hugging Face Papers. Use for "what are the hot AI papers", "trending ML research", "top papers this week".get_paperGet full detail for a paper by its arXiv id (e.g. "2312.00752"): title, authors, abstract, AI-generated summary and keywords, community upvotes, and counts of linked models / datasets / demo Spaces.get_repositoriesFind IMPLEMENTATIONS of a paper (by arXiv id): the linked GitHub repository plus the most popular Hugging Face models, demo Spaces, and datasets that implement or reproduce it — the "papers with code" view. Use for "code/implementation for <paper>", "models trained on <paper>".Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"lune-research-2": {
"command": "npx",
"args": [
"-y",
"@retrograde-labs/lune-mcp-server"
],
"env": {
"LUNE_API_KEY": "YOUR_LUNE_API_KEY_HERE"
}
}
}
}
{
"mcpServers": {
"paperswithcode": {
"command": "npx",
"args": [
"-y",
"@pipeworx/mcp-paperswithcode"
]
}
}
}