@lightpaperorg
基本信息
publish your essays, research papers and blogs at the speed of light
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"lightpaper": {
"command": "lightpaper-mcp",
"env": {
"LIGHTPAPER_API_KEY": "your-api-key"
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Lightpaper Mcp is an MCP server that provides 20 tools for the lightpaper.org publishing platform, enabling AI agents to publish content via a single HTTP call and receive permanent, beautifully formatted URLs readable by browsers, search engines, agents, and LLMs.
Run the FastAPI application locally via Docker Compose (docker compose up -d), create an account through the auth endpoint, verify an OTP code to obtain an API key, and then use the publish endpoint with that key. The MCP server is included in the repository under the mcp/ directory.
Agents can discover the API through the MCP server (20 tools), an OpenAPI spec at `/v1/openapi.json`, content negotiation on every URL, and a Google A2A Agent Card. `llms.txt` is served at the root as a courtesy signal.
Gravity measures how thoroughly an author has verified their identity across email, domain DNS, LinkedIn OAuth, and ORCID. It serves as a 1.0×–1.4× search ranking multiplier and affects eligibility for featured placement.
The server runs on Google Cloud Run with Cloud SQL PostgreSQL. Local development requires Docker Compose, Python 3 with virtual environment, and environment variables for Firebase Auth and LinkedIn OAuth.
Every document receives a quality score (0–100) at publish time covering structure, substance, tone, and attribution. Scores below 40 are noindexed; scores above 70 may be featured. Content is never refused based on score.
Accounts use Firebase Auth with email OTP verification. API keys are revocable and tied to real accounts. Content ownership is retained by the author under a display-only license for the platform.
🚀 The fast, Pythonic way to build MCP servers and clients.
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
A curated list of references for MLOps
Hindsight: Agent Memory That Learns
评论