CCM
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
retrogradelabs avatar

Lune Research

retrogradelabs/lune-mcp-server
authSTDIO, HTTPregistry active
Summary

Connects Claude to Lune Research's academic paper database through 12 tools covering search, retrieval, and subscriptions. You can run hybrid vector and BM25 searches across security, ML, NLP, CV, and systems venues, pull full paper text as markdown or JSON, walk citation graphs, and subscribe to conference updates. Works over stdio locally with an API key from your environment, or hit their hosted endpoint at mcp.luneresearch.com with a bearer token. Reach for this when you need your agent to literature review, track new papers in specific venues, or pull methodology guidance from their curated reproducibility corpus.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →

@retrograde-labs/lune-mcp-server

Official Model Context Protocol server for Lune Research.

Exposes 12 tools and 6 guided research workflows (prompts) for searching, retrieving, comparing, and fact-checking academic papers across security, ML, NLP, CV, and systems venues, plus retrieval over your own uploaded workspace documents. Two transports:

  • stdio: run locally via npx @retrograde-labs/lune-mcp-server. Reads LUNE_API_KEY from the environment.
  • Streamable HTTP: hosted at https://mcp.luneresearch.com. Pass your PAT or OAuth token as Authorization: Bearer ....

Quick start (Claude Desktop, Cursor, etc.)

{
  "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/settings/credentials.

Tools

ToolDescription
search_papersHybrid vector + BM25 search across the corpus
search_papers_manyRun many query variants in one call, RRF-merged
search_related_papersSemantically nearest papers to a given paper
get_paper_fulltextParsed full text (markdown or JSON)
get_paper_citationsCitation graph (cited_by or cites)
list_conferencesIndexed venues, optionally by category
get_conference_papersPaginated papers for a venue
extract_from_papersStructured field extraction across many papers
verify_claimsFact-check claims against the corpus with quotes
gather_evidenceJudge evidence sufficiency for a task, with gaps + next queries
search_research_guidanceCurated reproducibility / methodology corpus
get_research_guidance_docFull text of a guidance document

Prompts

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.

PromptWhat it doesKey arguments
/literature_reviewSurvey a topic and synthesise themes, foundational vs recent work, and open gapstopic (+ optional venues, since_year)
/find_related_workFrom your abstract, find and organise prior work to cite and distinguish your contribution fromabstract (+ optional venues)
/compare_papersBuild a structured comparison table across papers, read from full texttopic (+ optional columns)
/verify_draftFact-check a draft or list of claims against the corpus, with a verbatim quote per claimdraft
/trace_citationsTrace a paper's lineage: its foundations, what built on it, and adjacent workpaper
/research_methodologyGrounded advice on experiment design, ablations, evaluation, rebuttals, or venue choicequestion

Debugging with MCP Inspector

The repository pins MCP Inspector 2.3.0 and checks in a read-only server configuration for both protocol eras. Node 24 from .nvmrc satisfies the Inspector requirement.

With a PAT in LUNE_API_KEY, this builds the stdio server and opens the Inspector catalog with the PAT available to local processes. Select lune-stdio-modern to exercise 2026-07-28:

export LUNE_API_KEY=lune_xxxxxxxxxxxxxxxxxxxxxxxx
bun run mcp:inspect

With no LUNE_API_KEY, the same command opens the server catalog without an environment override. Select lune-remote-modern; Inspector starts OAuth when you connect. The launcher never passes an empty -e assignment.

The printed URL contains a one-time Inspector token. Open that URL instead of typing the port manually. The Inspector stays on loopback with authentication enabled.

The hosted-server mnemonic opens the same catalog without building stdio:

bun run mcp:inspect:remote

The web, CLI, and TUI clients share OAuth state on disk. After signing in once, the CLI can check the hosted server without opening another browser:

bun run mcp:inspect:remote:check

The local stdio checks use a non-production test token and a deliberately dead API URL. They validate connection, version negotiation, and the tool catalog without consuming quota:

bun run mcp:inspect:check
bun run mcp:inspect:check:legacy
bun run mcp:inspect:tui

The local and remote configs at apps/mcp/inspector.*.config.json pin protocolEra explicitly. Inspector defaults to the legacy era, so an unconfigured launch does not prove 2026-07-28 behavior. During debugging, pin Protocol beside Console for stdio or Network for HTTP. Test invalid tool arguments, missing prompt arguments, both protocol eras, and expired OAuth tokens as well as successful calls.

Run the frozen official 2026-07-28 server requirements with:

bun run mcp:conformance

The conformance harness binds only 127.0.0.1 and injects a local test token. Its baseline names individual checks for diagnostic capabilities Lune does not advertise, such as image tools and readable resources. Every applicable check still gates the run, and a stale baseline entry fails when support is added. Never write diagnostics to stdout on stdio. The server and its cache write diagnostics to stderr so JSON-RPC framing stays intact.

License

MIT

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →

Configuration

LUNE_API_KEY*secret

Lune personal access token. Generate one at https://luneresearch.com/dashboard/credentials.

Categories
AI & LLM ToolsSearch & Web Crawling
Registryactive
Package@retrograde-labs/lune-mcp-server
TransportSTDIO, HTTP
AuthRequired
UpdatedJun 3, 2026
View on GitHub

Related AI & LLM Tools MCP Servers

View all →
lutolabs avatar
MyAITwin

com.lutolearn/myaitwin

A personal RAG database you build from chat, so AI creates work that sounds like you.
com.mcpvillage avatar
MCPVillage

com.mcpvillage/website-builder

Build & edit your own website by talking to your LLM: pages, forms, SEO, analytics. Free to start.
meetdewey avatar
Dewey

com.meetdewey/dewey

Agentic search over your Dewey document collections from any MCP-compatible client.
gpitrella avatar
Memxus

com.memxus/memxus

Multi-platform AI memory. One save, recall everywhere—Claude, ChatGPT, Cursor, VS Code, and more.
mkc909 avatar
CloudClaw

com.mycloudclaw/cloudclaw

AI agent hosting platform: 37+ connectors, 181 tools, BYOK vault, marketplace.
wakizara avatar
Val

com.nyx-intelligence/val

QA agent for vibecoded apps. Real browser checks, your AI fixes them. Ship to green.