Lune

Lune is an MCP server that grounds AI agents in full-text computer science papers to eliminate hallucinations.

Lune Research is an MCP server designed to connect AI agents to top-tier computer science literature, research skills, and best practices. It provides full-text semantic search across core A and CCF A conference papers, citation tracing, and battle-tested research guidance. The system allows users to find research gaps, design evaluations, and draft related-work sentences with verified citations. It integrates with AI clients such as Claude Code, ChatGPT, Cursor, Antigravity, and Perplexity. Users can install Lune as a plugin or connector, use it via the command line interface, or access it through cloud agents on the web.

Lune at a glance

Best for: Researcher
Runs on: Web, CLI, API, Chrome extension
Pricing: Free plan; Pro $4.99/month; Max $9.99/month
Released: May 2026
Category: AI research tool
Website: luneresearch.com

Key features

Full-text semantic search
Citation tracing
Research best practices guidance
Claim checking
Full-text reading of top-tier papers

Use it for

Finding foundational papers and their claims
Locating research gaps and novelty checks
Designing evaluations with expected baselines and ablations
Drafting related-work sentences with checked citations

Companions

Tools that articles about Lune recommend using with it, each with its job.

Elicit — Elicit finds papers and extracts study details first.
Zotero — Zotero holds the checked bibliography.
Consensus — Consensus for fast evidence reads.
Perplexity — Real-time, cited answers on recent work.
Claude — Drafts and synthesis from your sources.

Alternatives to Lune

Agent Bayes — Builds defensible research mindmaps with page-level citations.
Scite — It uses direct publisher agreements to verify scientific claims with exact source links.
LLM Wiki Research — Compiles parallel agent research into source-backed markdown knowledge bases.
arXiv MCP Server — Enables local agent literature work with arXiv metadata and optional search.
Jevon Tane — It provides a rigorous, pre-registered framework for AI agents to conduct science together.
FAROS — Connects literature evidence, executable plans, and human review into an auditable research loop.
OpenResearch — Run parallel research workflows locally or on remote compute.
Paper2Agent — It enables direct interaction with research papers and automatic result reproduction.
AI Scientist v3 — Automates end-to-end scientific research from task descriptions to complete papers.
Exa — Provides high-accuracy web search and deep research endpoints for AI agents.
Auto Deep Researcher — Automates experiment operations to reduce manual babysitting of training loops.
Hypoarena — Provides a fully offline environment to test scientific discovery pipeline logic.

All Lune alternatives