Lune MCPFree
$0
10 requests / day
- All of Lune, no feature gates
- One personal account
- Sign in with Google or email
- Top up with credits any time
AI Research,free of AI slop
Connect AI agents to top-tier scientific literature, research skills and best practices, get grounded and trustworthy answers
Used by students and researchers from
- Dartmouth College
- Vector Institute
- University of Toronto
- University of Waterloo
- University of British Columbia
- Georgetown University
- Virginia Tech
- Carnegie Mellon University
- Stony Brook University
ClaudeDesktopLune MCP
CodexTerminalLune MCP
CursorEditorLune MCP
Literature Indexing + Retrieval Engine
Top-tier papers + Battle-tested research best practices
From literature review to publication
Wherever the work goes, the evidence goes with it.
Your agent grounds its answers in top-tier papers and battle-tested research practices, so nothing rests on guesswork.
Lune indexes every paper in full-text, so that your agent compiles its answers based on the exact sentences, numbers, and equations from prior works.
Claude+Lune
You
I'm new to retrieval-augmented generation. What are the foundational papers, and what exactly do they claim?
Your agent
calledLunesearch_papers ·get_paper_fulltext [1]
Three papers anchor the area: RAG [1] introduced the retrieve-then-generate recipe, REALM [2] pretrained retrieval end to end, and Fusion-in-Decoder [3] scaled it across many passages. More recent work makes retrieval adaptive: Self-RAG [4] lets the model decide when to retrieve and critique what it generates. Here is RAG's setup, in its own words:
full text · Lewis et al., NeurIPS 2020
We introduce RAG models where the parametric memory is a pre-trained seq2seq model and the non-parametric memory is a dense vector index of Wikipedia, accessed with a pre-trained neural retriever.
Stop Reference Hallucinations
Only where the field actually moves.
Lune indexes only high-quality venues based on CORE and CCF rankings, in full. No open-web filler, no clickbait, so every answer stays grounded in real papers you can cite.
Knowledge cutoff
Top-tier venues
Lune only indexes high-quality venues based on CORE and CCF rankings, in full text.
No missed SOTAs
Using Lune, new accepted papers at top-tier venues reach your agent the day they post. The knowledge cutoff keeps moving.
Beyond papers: the best-practices library
A curated corpus on peer review, novelty, ablation design, evaluation, and venue choice. This is the battle-tested half of grounding, what reviewers at top venues actually expect, surfaced to your agent only when it is relevant.
Insights and guidance extracted from talks, interviews, notes, and publications, by the voices that shaped the fields.
One platform. Three ways to connect
However your agent runs, Lune meets it there.
Pick the surface that fits how you work. The grounding underneath is identical.
Available now
MCP tools
Access Lune's core features
Connect once to Claude, Cursor, Codex and more. Your agent gains search, citation trails, full text, venue feeds, and methodology, all grounded.
Available now
The CLI
Install & use Lune from the command line
Sign in, install Lune into any client, switch teams, and manage your plan without leaving the terminal.
$ npm install -g @retrograde-labs/lune-cliOne sign-in. Works across every AI app you already use.
Pricing
We have a plan for every kind of researcher.
Pick a plan with a standard daily allowance. If you go past it, just top up extra usage credits.
Pro
Popular$4.99
/ month · 300 requests / day
- Everything in Free
- Share plan and credits with your team
- Connect any AI client you use
- Top up with credits any time
Max
$9.99
/ month · 600 requests / day
- Everything in Pro
- Up to 10 teammates per team
- Faster burst for heavy days
- Priority email support
Busy day? Top up with credits at $0.99 for 300 extra requests. Credits never expire, and they work on every plan.
Trustworthy AI for Scientific Research
Free to start. No credit card required.
Try Lune