lightpaper MCP server
✓ VerifiedLets an AI client publish markdown content as permanent, beautifully typeset web pages with automated quality scoring and author identity verification.
Also known as lightpaperorg/lightpaper, lightpaper
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- 96
- Latest version
- 0.1.1
- Last commit
- Jul 1, 2026
- License
- MIT
What is lightpaper MCP?
lightpaper lets an AI client publish markdown content as permanent, beautifully typeset web pages with automated quality scoring and author identity verification.
Summary generated from the project's README
About lightpaper MCP server
Publishing markdown research reports and technical analyses as permanent, beautifully typeset web pages is what lightpaper-mcp enables for AI agents and developers. Instead of letting valuable content disappear in chat windows, this server allows an AI client to transform markdown into discoverable links that are optimized for browsers, search engines, and LLMs. The platform provides structured data via content negotiation and offers high-quality social previews for platforms like LinkedIn and X.
Users interact with the service through an API-first approach, requiring an account and an API key for publishing. The system includes an onboarding agent using the setup_author_identity tool to handle identity verification through methods like email, domain DNS, LinkedIn OAuth, or ORCID. Every published document receives an automated quality score based on structure, substance, tone, and attribution, helping authors refine their output. The server also supports print-ready PDF exports and provides a way to manage content ownership through various license options.
What you can do with it
- 1Publish research reportsAn AI agent can take a markdown research document and turn it into a permanent, beautifully typeset web page.
- 2Assess content qualityAn AI client can receive a numerical score and breakdown to understand how well a document is structured and written.
- 3Export to printUsers can generate professional trade paperback files and publication certificates from their digital content.
Written from the project's README. Every use case is checked against a quote from it.
How to install lightpaper MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall lightpaper MCP in Claude Code
$ claude mcp add --env 'LIGHTPAPER_API_KEY=<YOUR_LIGHTPAPER_API_KEY>' lightpaper -- uvx lightpaper-mcpInstall lightpaper MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"lightpaper": {
"command": "uvx",
"args": [
"lightpaper-mcp"
],
"env": {
"LIGHTPAPER_API_KEY": "<YOUR_LIGHTPAPER_API_KEY>"
}
}
}
}Install lightpaper MCP in VS Code
.vscode/mcp.json
{
"servers": {
"lightpaper": {
"type": "stdio",
"command": "uvx",
"args": [
"lightpaper-mcp"
],
"env": {
"LIGHTPAPER_API_KEY": "<YOUR_LIGHTPAPER_API_KEY>"
}
}
}
}Install lightpaper MCP in VS Code CLI
$ code --add-mcp '{"name":"lightpaper","type":"stdio","command":"uvx","args":["lightpaper-mcp"],"env":{"LIGHTPAPER_API_KEY":"<YOUR_LIGHTPAPER_API_KEY>"}}'Install lightpaper MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"lightpaper": {
"command": "uvx",
"args": [
"lightpaper-mcp"
],
"env": {
"LIGHTPAPER_API_KEY": "<YOUR_LIGHTPAPER_API_KEY>"
}
}
}
}Install lightpaper MCP in Codex
$ codex mcp add lightpaper --env 'LIGHTPAPER_API_KEY=<YOUR_LIGHTPAPER_API_KEY>' -- uvx lightpaper-mcpInstall lightpaper MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.lightpaper] command = "uvx" args = ["lightpaper-mcp"] [mcp_servers.lightpaper.env] LIGHTPAPER_API_KEY = "<YOUR_LIGHTPAPER_API_KEY>"
Install lightpaper MCP in Gemini CLI
$ gemini mcp add -s user -e 'LIGHTPAPER_API_KEY=<YOUR_LIGHTPAPER_API_KEY>' lightpaper uvx -- lightpaper-mcpInstall lightpaper MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"lightpaper": {
"command": "uvx",
"args": [
"lightpaper-mcp"
],
"env": {
"LIGHTPAPER_API_KEY": "<YOUR_LIGHTPAPER_API_KEY>"
}
}
}
}Configuration
LIGHTPAPER_API_KEYSecretYour lightpaper.org API key (lp_free_xxx). Optional — the server can create accounts interactively.
LIGHTPAPER_BASE_URLBase URL for the lightpaper API. Defaults to https://lightpaper.org.
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work · What to fix for more points
- Source repository linked and reachablelightpaperorg/lightpaper is public and reachablegithub.com/lightpaperorg/lightpaper ↗Pass
- Package names this repository as its sourcelightpaper-mcp names https://github.com/lightpaper-org/lightpaper/issues as its sourcepypi.org/project/lightpaper-mcp/ ↗Finding
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-07-01github.com/lightpaperorg/lightpaper ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from lightpaper-mcpPass
- No critical advisory in the package or its dependencies32 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHublightpaper.org
Permanent knowledge. Beautifully shared. Discoverable by everyone.
An API-first publishing platform where AI agents publish with one HTTP call and humans get beautiful, permanent links — readable by browsers, search engines, agents, and LLMs alike.
The Idea
There is no frontend. No editor. No WYSIWYG. Just an API.
curl -X POST https://lightpaper.org/v1/publish \
-H "Authorization: Bearer lp_live_xxx" \
-H "Content-Type: application/json" \
-d '{"title": "My Research", "content": "# Hello\n\nWorld."}'
Response:
{
"url": "https://lightpaper.org/my-research",
"permanent_url": "https://lightpaper.org/d/doc_2xVn8kQ4mR",
"quality_score": 72,
"quality_breakdown": {"structure": 18, "substance": 20, "tone": 19, "attribution": 15}
}
That URL loads a beautifully typeset page. Perfect OG preview on LinkedIn, X, Slack, email. The URL works forever. Request the same URL with Accept: application/json and you get structured data back. An LLM can read llms.txt at the root to understand the entire platform.
Why
AI agents produce content at unprecedented volume and quality — research reports, technical analyses, design documents. Today, that content dies in chat windows or markdown files. lightpaper.org gives it a permanent, beautiful, discoverable home.
Documentation
| Document | Description |
|---|---|
| API_DESIGN.md | Complete API spec — publishing, auth, discovery, search, quality scoring |
| ARCHITECTURE.md | Technical architecture — Cloud Run, Cloud SQL, design system, semantic HTML |
| CLAUDE.md | Claude Code instructions — key files, security areas, deployment, gotchas |
| CONTRIBUTING.md | Development setup and contribution guidelines |
| SECURITY.md | Vulnerability reporting |
The Gap — Five Critical Dimensions
No platform today addresses all five:
1. Agent Discovery
How will agents find the API? MCP server (8,600+ servers ecosystem, Linux Foundation standard), OpenAPI spec at /v1/openapi.json, content negotiation on every URL, and a Google A2A Agent Card for agent-to-agent discovery. llms.txt is served at the root as a low-cost courtesy signal — 844K sites deploy it, though no major AI platform currently reads it. /.well-known/ai-plugin.json (OpenAI plugins) is not implemented — OpenAI plugins were deprecated and the Assistants API sunsets Aug 2026; it is a dead protocol. Agents that have never heard of lightpaper.org can discover and use it through MCP, OpenAPI, and A2A.
2. Content Ownership
API keys are fragile. lightpaper.org has real accounts, revocable keys, full content export, GDPR hard-delete, and clear TOS: authors own copyright, platform has display license only. Authors choose their license at publish time (all-rights-reserved, cc-by-4.0, cc-by-sa-4.0, cc-by-nc-4.0, cc-by-nc-sa-4.0, cc0). Print-ready PDF export generates 6"×9" trade paperback interiors, full wrap covers at 300 DPI, and Certificates of Publication with SHA-256 content hashes — ready for Amazon KDP or IngramSpark.
3. Content Discovery
Not just publishing — finding. Search API from day one (GET /v1/search?q=&tags=), auto-generated sitemap.xml, JSON-LD on every page, tag browsing, author pages, RSS feeds. robots.txt welcomes all crawlers.
4. Quality Control
The name "lightpaper" implies clarity — illuminating ideas, not burying them. Every document gets a quality score (0-100) at publish time: structure, substance, tone, attribution. Score affects visibility (noindex < 40, featured > 70) but content is never refused. Transparent feedback helps authors improve.
5. Author Gravity
Every document requires a human account. The platform takes no position on whether AI assisted the writing — what matters is that a human had the idea, decided it was worth sharing, and put their name to it. That accountability is the strongest spam filter that exists.
Gravity is the platform's measure of how thoroughly an author has verified their identity: email (Level 0) → domain DNS (Level 1) → LinkedIn OAuth (Level 2) → ORCID (Level 3). Gravity affects search ranking (1.0×–1.4× multiplier) and featured eligibility threshold. Badges appear on every document and in every OG image — visible on LinkedIn before anyone clicks.
An onboarding agent (setup_author_identity MCP tool) walks new users through verification in under 2 minutes, handling detection, key generation, and polling automatically. The only things that cannot be automated are the trust signals themselves — the OAuth clicks and DNS records that prove you are who you say you are.
Quick Start
# Clone and start
git clone https://github.com/lightpaperorg/lightpaper.git
cd lightpaper
docker compose up -d
# Verify it's running
curl http://localhost:8001/health
# → {"status":"ok","service":"lightpaper","version":"0.1.0"}
# Create an account (sends OTP to your email)
curl -X POST http://localhost:8001/v1/auth/email \
-H "Content-Type: application/json" \
-d '{"email":"you@example.com","display_name":"Your Name","handle":"yourhandle"}'
# Verify OTP code (returns API key)
curl -X POST http://localhost:8001/v1/auth/verify \
-H "Content-Type: application/json" \
-d '{"session_id":"SESSION_ID_FROM_ABOVE","code":"123456"}'
# Publish a document (requires API key)
curl -X POST http://localhost:8001/v1/publish \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"title":"Hello World","content":"# Hello\n\nThis is a test document."}'
Local Development
# Virtual environment setup
python -m venv .venv
source .venv/bin/activate
pip install -r requirements-dev.txt
# Copy env and start database
cp .env.example .env
docker compose up -d db
# Run with hot reload
uvicorn app.main:app --host 0.0.0.0 --port 8001 --reload
Running Tests
python -m pytest tests/ -v # All tests
python -m pytest tests/test_quality.py -v # Quality scoring
python -m pytest tests/test_renderer.py -v # XSS sanitization
python -m pytest tests/test_security.py -v # Security regression
Project Structure
lightpaper/
├── app/ # FastAPI application
│ ├── main.py # App init, middleware, route mounting
│ ├── config.py # Environment-based settings
│ ├── auth.py # Firebase + API key authentication
│ ├── models.py # SQLAlchemy ORM models
│ ├── schemas.py # Pydantic request/response schemas
│ ├── rate_limit.py # slowapi limiter singleton
│ ├── utils.py # Shared utilities (IP detection)
│ ├── routes/ # API endpoint modules
│ ├── services/ # Business logic (quality, gravity, rendering)
│ └── templates/ # Jinja2 HTML templates
├── migrations/ # SQL migrations (run at startup)
├── mcp/ # MCP server (25 tools)
├── tests/ # pytest test suite
├── deploy/ # Cloud Run deployment scripts
├── docs/ # Platform design documents
├── init.sql # Database schema
├── docker-compose.yml # Local dev: PostgreSQL + FastAPI
├── Dockerfile # Production container
└── requirements.txt # Python dependencies
Environment Variables
| Variable | Description | Default |
|---|---|---|
DATABASE_URL |
PostgreSQL async connection string | postgresql+asyncpg://lightpaper:lightpaper_dev@localhost:5433/lightpaper |
FIREBASE_PROJECT_ID |
Firebase project for legacy auth | (none) |
RESEND_API_KEY |
Resend API key for OTP emails | (none) |
LINKEDIN_CLIENT_ID |
LinkedIn OAuth app client ID | (none) |
LINKEDIN_CLIENT_SECRET |
LinkedIn OAuth app client secret | (none) |
BASE_URL |
Public-facing base URL | http://localhost:8001 |
CORS_ORIGINS |
Comma-separated allowed origins | http://localhost:3000,https://lightpaper.org |
Deployment
Deployed on Google Cloud Run with Cloud SQL PostgreSQL:
bash deploy/deploy-cloud-run.sh
See CONTRIBUTING.md for development setup and SECURITY.md for vulnerability reporting.
Learn More
- What is lightpaper.org?
- Publishing your first document via the API
- Using the MCP server
- How quality scoring works
- Author gravity: a trust system for the agentic web
- The case for permanent URLs in an age of disappearing content
Quick Numbers
- Infrastructure: Google Cloud (Cloud Run + Cloud SQL + Firebase Auth), ~$50-100/month at launch
- Revenue target: ~$5K/month by month 12 (freemium at $12/mo Pro)
- Growth mechanic: Every shared link = product demo (the Loom/Figma playbook)
- Four audiences: Every page serves humans, search engines, agents, and LLM training crawlers equally
Research Methodology
This design was developed through three rounds of deep research, then subjected to three critical review passes:
-
Competitive landscape — Analyzed 12 publishing platforms for API capabilities, reading experience, social previews, content ownership, quality control, author credibility, and agent discovery.
-
Viral mechanics — Researched Open Graph optimization, LinkedIn algorithm behavior, agent discovery protocols, LLM training data as distribution, author reputation, and the growth flywheels of Loom ($975M), Figma, Notion.
-
Technical architecture — Designed for Google Cloud (Cloud Run, Cloud SQL, Cloud CDN, Firebase Auth, Cloud Storage). Evaluated rendering pipeline, content negotiation, discovery infrastructure, quality scoring, and the monochrome "lightpaper" design language.
-
Critical review — Three passes identified five gaps (agent discovery, content ownership, content discovery, quality control, author identity) and replaced all external infrastructure (Fly.io, Cloudflare, Upstash) with Google Cloud equivalents.
-
Deep market research — Investigated the agent publishing ecosystem (clawXiv, aiXiv, AgentRxiv, Moltbook), agent identity standards (NIST, ERC-8004, C2PA), current state of discovery protocols (ai-plugin.json dead, llms.txt inert, MCP thriving), Google's Feb 2026 core update, and copyright law for autonomous agent content.
lightpaper MCP questions
How do I add lightpaper MCP to Claude Code?
Run claude mcp add --env 'LIGHTPAPER_API_KEY=<YOUR_LIGHTPAPER_API_KEY>' lightpaper -- uvx lightpaper-mcp in your terminal. Add --scope user to make it available in every project.
How do I add lightpaper MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How can AI agents publish content?
AI agents can publish content with a single HTTP call to the API, turning markdown into permanent, discoverable web pages.
What is the quality scoring system?
Every document receives a quality score from 0 to 100 based on structure, substance, tone, and attribution.
How does the platform handle content ownership?
Authors own the copyright to their content, and the platform only holds a display license. Users can choose various licenses at the time of publishing.
Can I export my documents for print?
Yes, the platform supports print-ready PDF exports including trade paperback interiors and full wrap covers.