Paper Lantern MCP Server

@paperlantern-ai

Basic information

About Paper Lantern MCP Server

Paper Lantern setup CLI - one-line install to configure Claude Code, Cursor, Windsurf, Copilot, Codex, and Gemini CLI with Paper Lantern

#research-papers #arxiv #ai-research #coding-agents #claude-code #cursor #windsurf #remote-server #streamable-http #literature #knowledge

Paper Lantern MCP Server config

Add this server to your MCP-compatible client using the configuration below.

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

Paper Lantern MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list directly from this server's endpoint using the button above.

Overview

What is Paper Lantern?

Paper Lantern is a research intelligence tool for AI coding agents, providing access to over 2 million computer science research papers. It integrates via the Model Context Protocol (MCP) with a single command setup, helping agents make informed technical decisions.

How to use Paper Lantern?

Run npx paperlantern@latest in your terminal, then select your preferred AI agents and log in through OAuth. The setup CLI automatically configures the MCP server and installs agent rules.

Key features of Paper Lantern

One‑command setup via npx paperlantern@latest
OAuth authentication for secure access
Automatic MCP server configuration for supported agents
Agent rules installed so agents know when to use Paper Lantern
Five tools for research exploration, deep dives, comparisons, feasibility checks, and feedback

Use cases of Paper Lantern

Surveying multiple approach families with evidence and tradeoffs
Investigating a single technique in depth, including hyperparameters and failure modes
Comparing two or three candidate approaches side‑by‑side
Getting a GO / PROTOTYPE / RECONSIDER verdict based on project constraints
Providing feedback to improve future research suggestions

Frequently asked questions

Which AI agents are supported by Paper Lantern?

Claude Code, Cursor, Windsurf, GitHub Copilot (VS Code), Codex, Gemini CLI, and Cline are supported. For agents not listed, see the manual setup guide at paperlantern.ai/docs.

How do I set up Paper Lantern manually?

Manual setup instructions and per‑agent configuration snippets are available at [paperlantern.ai/docs](https://paperlantern.ai/docs). The site also provides the raw MCP endpoint.

When does Paper Lantern activate during coding?

Paper Lantern activates only when your agent is making technical decisions (e.g., choosing algorithms, architectures, or techniques). It does not activate for syntax questions, library lookups, debugging, or general programming tasks.

What tools does Paper Lantern provide to my agent?

The agent receives five tools: `explore_approaches`, `deep_dive`, `compare_approaches`, `check_feasibility`, and `give_feedback`. Each serves a specific research purpose, from surveying approaches to providing feedback.

Does Paper Lantern require any additional dependencies?

The setup command uses `npx`, which requires Node.js and npm. No other dependencies are mentioned in the README.

Comments

More Developer Tools MCP servers

Routebase

Routebase keeps your API's design, docs, contract tests, mocks and monitoring in one living OpenAPI spec so they can't drift apart. Agents work on that same source of truth, under your team's permissions.

ArtiBot Cloud MCP - Zhijiangyun 智匠云

bofob

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

Vibgrate MCP

Vibgrate

Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

LastPing

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci