Lune Mcp Server — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Lune Mcp Server (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<!-- mcp-name: com.luneresearch/lune -->
Official Model Context Protocol server for Lune Research.
Exposes 16 tools and 6 guided research workflows (prompts) for searching, retrieving, comparing, fact-checking, and subscribing to academic papers across security, ML, NLP, CV, and systems venues. Two transports:
npx @retrograde-labs/lune-mcp-server. Reads LUNE_API_KEY from the environment.https://mcp.luneresearch.com/mcp. Pass your PAT or OAuth token as Authorization: Bearer ....{
"mcpServers": {
"lune-research": {
"command": "npx",
"args": ["-y", "@retrograde-labs/lune-mcp-server"],
"env": {
"LUNE_API_KEY": "lune_your_personal_access_token"
}
}
}
}Get your token at https://luneresearch.com/dashboard/credentials.
| Tool | Description |
|---|---|
search_papers | Hybrid vector + BM25 search across the corpus |
search_papers_many | Run many query variants in one call, RRF-merged |
search_related_papers | Semantically nearest papers to a given paper |
get_paper_fulltext | Parsed full text (markdown or JSON) |
get_paper_citations | Citation graph (cited_by or cites) |
list_conferences | Indexed venues, optionally by category |
get_conference_papers | Paginated papers for a venue |
extract_from_papers | Structured field extraction across many papers |
verify_claims | Fact-check claims against the corpus with quotes |
search_research_guidance | Curated reproducibility / methodology corpus |
get_research_guidance_doc | Full text of a guidance document |
list_subscriptions | Active conference subscriptions |
subscribe_conference | Follow a conference for new-paper updates |
unsubscribe_conference | Stop following a conference |
get_subscription_updates | New papers across every subscription |
Reusable research workflows, surfaced by MCP clients as slash commands (e.g. /literature_review). Each runs a guided, multi-tool sequence grounded in the corpus, so common research tasks are one command instead of hand-orchestrating the tools.
| Prompt | What it does | Key arguments |
|---|---|---|
/literature_review | Survey a topic and synthesise themes, foundational vs recent work, and open gaps | topic (+ optional venues, since_year) |
/find_related_work | From your abstract, find and organise prior work to cite and distinguish your contribution from | abstract (+ optional venues) |
/compare_papers | Build a structured comparison table across papers, read from full text | topic (+ optional columns) |
/verify_draft | Fact-check a draft or list of claims against the corpus, with a verbatim quote per claim | draft |
/trace_citations | Trace a paper's lineage: its foundations, what built on it, and adjacent work | paper |
/research_methodology | Grounded advice on experiment design, ablations, evaluation, rebuttals, or venue choice | question |
MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.