Skip to main content
Glama

AI News Aggregator

Agregador de notícias de IA, papers acadêmicos e repositórios trending de 10 fontes confiáveis.

API Status Python License


Quick Start

Usar API (sem instalação):

curl "https://mcp-ai-news.onrender.com/news?days=7&limit=5"

Instalar MCP para Claude Code:

git clone https://github.com/LauraMattz/mcp_ai_news.git && cd mcp_ai_news
pip install -r requirements.txt
# Recarregue Claude Code (Ctrl+Shift+P → Reload Window)

Related MCP server: mcp-ai-news-server

API Pública

Base: https://mcp-ai-news.onrender.com | Docs: Swagger UI

Endpoint

Descrição

/news?days=7&limit=10

Todas as notícias

/search?q=GPT

Busca por palavra-chave

/papers?days=7

Papers do ArXiv

/github?days=7

Repos trending

Fontes: OpenAI, Anthropic, Google AI, DeepMind, Hugging Face, MIT Tech Review, TechCrunch, The Verge, ArXiv (cs.AI/cs.LG/cs.CL/cs.CV/stat.ML), GitHub

Features: Cache 15 min • CORS habilitado • Gratuito • ~180+ itens agregados


Instalação

MCP Server (Claude Code)

O .mcp.json já está configurado na raiz do projeto. Após git clone e pip install, apenas recarregue Claude Code.

Para Claude Desktop: Adicione ao claude_desktop_config.json (Windows/Mac/Linux paths):

{
  "mcpServers": {
    "ai-news": {
      "command": "python",
      "args": ["/caminho/completo/para/server.py"]
    }
  }
}

REST API (Local)

python api.py
# Acesse: http://localhost:8000/docs

Uso

MCP (Claude Code/Desktop):

"Liste as últimas notícias de IA"
"Busque conteúdo sobre transformers"
"Mostre papers do ArXiv sobre computer vision"

API REST:

curl "https://mcp-ai-news.onrender.com/news?days=7&limit=20"
curl "https://mcp-ai-news.onrender.com/search?q=GPT&days=14"
curl "https://mcp-ai-news.onrender.com/papers?days=3&max_results=10"

Documentação completa: Swagger UIReDoc


Desenvolvimento

Adicionar fonte RSS:

# Em server.py e api.py
FONTES_RSS["nova_fonte"] = {
    "nome": "Nome", "url": "https://...", "ativa": True
}

Testar:

python server.py  # MCP Server
python api.py     # REST API → http://localhost:8000/docs
npx @modelcontextprotocol/inspector python server.py  # MCP Inspector

Estrutura:

├── server.py      # MCP Server (stdio)
├── api.py         # REST API (FastAPI)
├── .mcp.json      # Config Claude Code
└── render.yaml    # Deploy config

Licença

MIT License - Ver LICENSE

Desenvolvido por Laura MattosLinkedIn

Stack: MCPFastAPIArXiv API

A
license - permissive license
Not graded
quality - not tested
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    Not graded
    quality
    C
    maintenance
    An AI-powered news aggregator MCP server that fetches live news from multiple sources, provides AI summaries via Claude, and performs sentiment analysis and trending topic detection.
  • F
    license
    Not graded
    quality
    B
    maintenance
    An MCP server providing real-time access to tech news from Hacker News, GitHub trending repositories, ArXiv papers, and dev.to articles, with capabilities for deep dives and cross-source comparisons.
  • F
    license
    Not graded
    quality
    C
    maintenance
    Local MCP server that ingests and normalizes recent AI, tech, and research news from multiple sources, exposing tools for media agents to query and retrieve article content on demand.

View all related MCP servers

Related MCP Connectors

  • Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.

  • An MCP server that gives your AI access to the source code and docs of all public github repos

  • A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/LauraMattz/mcp_ai_news'

If you have feedback or need assistance with the MCP directory API, please join our Discord server