Paper Lantern

ai.paperlanternPublished by paperlantern.aiOfficial publisherv0.3.1Updated Oct 27, 2026

Research intelligence for AI coding agents. 2M+ CS papers with evidence and tradeoffs.

VerifiedStreamable HTTPWeb executableKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Paper Lantern gives AI coding agents research intelligence over 2M+ computer science papers, with evidence, tradeoffs and implementation guidance.

What you can do
  • Survey 4-6 approach families for a problem, with evidence and tradeoffs
  • Investigate one technique in depth, including implementation, hyperparameters and failure modes
  • Compare 2-3 candidate approaches side by side
  • Give a GO / PROTOTYPE / RECONSIDER feasibility verdict against stated constraints
  • Send feedback on what helped and what did not
When to use it
Useful when an agent is making technical decisions where research evidence would help, such as choosing between algorithms, architectures or techniques. It is not intended for syntax questions, library lookups, debugging or general programming tasks.
Requirements
A remote MCP endpoint, or the setup CLI run through npx, which requires Node.js. Setup authenticates via OAuth in a browser and configures the MCP server plus agent rules for supported agents such as Claude Code, Cursor, Windsurf, GitHub Copilot, Codex, Gemini CLI and Cline. Manual configuration is possible for other clients.
Before you install
Setup opens a browser for OAuth login, so an account with the provider is created or used. The setup CLI writes MCP server configuration and agent rules into your agent clients. Queries and feedback are sent to the provider's service.

Installation

In SourceWeft

  1. Open Paper Lantern in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.paperlantern%2Fcode/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "paper-lantern": {
      "type": "http",
      "url": "https://mcp.paperlantern.ai/chat/mcp"
    }
  }
}

README

paperlantern

Research intelligence that makes your AI coding agent smarter - one command setup.

Paper Lantern gives your AI coding agent access to 2M+ CS research papers - the right technique for your problem, with tradeoffs, benchmarks, and implementation guidance.

Quick start

npx paperlantern@latest

That's it. Pick your agents, log in, and Paper Lantern is configured.

Supported agents

  • Claude Code
  • Cursor
  • Windsurf
  • GitHub Copilot (VS Code)
  • Codex
  • Gemini CLI
  • Cline

Prefer to set up manually, or using a client not listed above? See paperlantern.ai/docs for per-agent config snippets and the raw MCP endpoint.

What it does

The setup CLI:

  1. Authenticates via OAuth (opens browser)
  2. Configures the MCP server for your selected agents
  3. Installs agent rules so your agent knows when to use Paper Lantern

Tools available

Once configured, your agent gets these tools:

ToolWhat it does
explore_approachesSurvey 4-6 approach families with evidence and tradeoffs
deep_diveInvestigate one technique in depth - implementation, hyperparameters, failure modes
compare_approachesSide-by-side comparison of 2-3 candidates
check_feasibilityGO / PROTOTYPE / RECONSIDER verdict given your constraints
give_feedbackTell us what helped and what didn't

When your agent uses Paper Lantern

Paper Lantern activates when your agent is making technical decisions where research evidence could improve the outcome - choosing between algorithms, architectures, or techniques.

It does not activate for syntax questions, library lookups, debugging, or general programming tasks.

Links

Source: README.md at commit f3aa9c5

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v0.3.1LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts