convez.ai
PluginBusca & PesquisaIntermediário
bh-rat

Context Awesome

bh-rat/context-awesome

Acesso a curadoria comunitária de recursos (8500+ awesome lists) para agentes IA

Ver no GitHub
BomPluginScore · de 0 a 100

MCP server e CLI que fornece acesso a mais de 8500 listas awesome curadas pela comunidade, com 1+ milhão de recursos vetados. Ideal para agentes IA localizarem rapidamente as melhores ferramentas, bibliotecas e referências sem depender de buscas web aleatórias.

Instalação

$npx convez-ai bh-rat/context-awesome

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
62
Forks
11
Acompanhando
0
Saúde
42%
Último commit
há 5 meses
Versão
—
Issues abertas
3
Contribuidores
1

Casos de uso

  • Agentes de knowledge workers buscarem referências relevantes para tarefas especializadas
  • Pesquisa profunda com agregação rápida de recursos de alta qualidade
  • Agentes de busca descobrirem as melhores ferramentas por tema ou tecnologia
  • Integração em workflows CI/CD para validação e documentação de dependências

Veredito

Ferramenta sólida que democratiza acesso a curadoria comunitária para agentes. Implementação dupla (MCP + CLI) oferece flexibilidade, mas a utilidade depende da qualidade e atualização das awesome lists indexadas pelo backend.

README

A tradução para o português deste README ainda está na fila.

context-awesome : awesome references for your agents Awesome

MCP Server

A Model Context Protocol (MCP) server that provides access to all the curated awesome lists and their items. It can provide the best resources for your agent from sections of the 8500+ awesome lists on github and more then 1mn+ (growing) awesome row items.

What are Awesome Lists? Awesome lists are community-curated collections of the best tools, libraries, and resources on any topic - from machine learning frameworks to design tools. By adding this MCP server, your AI agents get instant access to these high-quality, vetted resources instead of relying on random web searches.

Perfect for :

  1. Knowledge worker agents to get the most relevant references for their work
  2. The source for the best learning resources
  3. Deep research can quickly gather a lot of high quality resources for any topic.
  4. Search agents

https://github.com/user-attachments/assets/babab991-e4ff-4433-bdb7-eb7032e9cd11

Two Ways to Use Context Awesome

ModeInstallGood for
MCP Serverpoint your agent at the hosted URL or spawn context-awesome-mcpClaude Desktop, Cursor, Windsurf, VS Code — agents that natively speak MCP
CLInpm install -g context-awesomeScripts, shell workflows, editors without MCP support, CI jobs

Both modes ship from the same npm package (context-awesome) and hit the same hosted backend.

MCP Tools

Every MCP tool has a 1:1 CLI subcommand — the server and the CLI expose the same operations.

ToolCLI equivalentWhat it does
find_awesome_sectioncontext-awesome sections <query...>Discover sections/categories across awesome lists matching a query
search_awesome_itemscontext-awesome search <query...>Full-text search across individual items (tools/libraries/resources)
get_awesome_itemscontext-awesome items <target>Fetch items from a known list + section, token-budgeted

CLI Commands

The CLI (context-awesome) talks directly to the hosted backend. For the MCP server, use the separate context-awesome-mcp binary (see Installation — MCP Clients below).

context-awesome <command> [options]

Commands:
  sections <query...>        Find sections matching a query
  search <query...>          Search items (e.g., context-awesome search "postgres orm")
  items <target>             Fetch items from a list (by owner/repo or listId)

Globals:
  --api-host <url>           Backend API host (env: CONTEXT_AWESOME_API_HOST)
  --api-key <key>            API key (env: CONTEXT_AWESOME_API_KEY)
  --json                     Emit raw JSON (for scripts)

Install the CLI

npm install -g context-awesome
context-awesome --help
context-awesome search "rate limiter"
context-awesome sections "graph databases"

Use the CLI without installing

npx context-awesome search "vector database"

Installation — MCP Clients

Remote Server (Recommended)

Context Awesome is available as a hosted MCP server. No installation required.

Go to: Settings → Cursor Settings → MCP → Add new global MCP server

{
  "mcpServers": {
    "context-awesome": {
      "url": "https://www.context-awesome.com/api/mcp"
    }
  }
}
claude mcp add --transport http context-awesome https://www.context-awesome.com/api/mcp

Settings → Connectors → Add Custom Connector.

  • Name: Context Awesome
  • URL: https://www.context-awesome.com/api/mcp

Use the same URL (https://www.context-awesome.com/api/mcp) with each client's "add remote MCP" UI. See the dedicated sections below for exact snippets.

Local stdio (Claude Desktop, offline-capable)

{
  "mcpServers": {
    "context-awesome": {
      "command": "npx",
      "args": ["-y", "context-awesome-mcp", "serve", "--transport", "stdio"],
      "env": {
        "CONTEXT_AWESOME_API_HOST": "https://api.context-awesome.com"
      }
    }
  }
}

Local HTTP transport (for custom integrations)

npx context-awesome-mcp serve --transport http --port 3001
# then point your client at http://localhost:3001/mcp

Local Development

git clone https://github.com/bh-rat/context-awesome.git
cd context-awesome
npm install
npm run build

# CLI
./build/cli.js search "graph databases"

# MCP server (stdio)
./build/index.js --transport stdio

# MCP Inspector
npm run inspector

Backend service

This MCP server and CLI connect to backend API service that handles the heavy lifting of awesome list processing.

The backend service will be open-sourced soon, enabling the community to contribute to and benefit from the complete context-awesome ecosystem.

Additional Installation Methods

{
  "mcpServers": {
    "context-awesome": {
      "url": "https://www.context-awesome.com/api/mcp"
    }
  }
}
{
  "context_servers": {
    "context-awesome": {
      "url": "https://www.context-awesome.com/api/mcp"
    }
  }
}
  1. Click the hamburger menu
  2. Select Settings
  3. Navigate to Tools
  4. Click + Add MCP
  5. Enter URL: https://www.context-awesome.com/api/mcp
  6. Name: Context Awesome
{
  "mcpServers": {
    "context-awesome": {
      "type": "streamable-http",
      "url": "https://www.context-awesome.com/api/mcp"
    }
  }
}
{
  "mcpServers": {
    "context-awesome": {
      "httpUrl": "https://www.context-awesome.com/api/mcp"
    }
  }
}
"mcp": {
  "context-awesome": {
    "type": "remote",
    "url": "https://www.context-awesome.com/api/mcp",
    "enabled": true
  }
}
  1. Go to Settings -> Tools -> AI Assistant -> Model Context Protocol (MCP)
  2. Click + Add
  3. Configure URL: https://www.context-awesome.com/api/mcp
  4. Click OK and Apply
  1. Navigate Kiro > MCP Servers
  2. Click + Add
  3. Configure URL: https://www.context-awesome.com/api/mcp
  4. Click Save
{
  "mcpServers": {
    "context-awesome": {
      "url": "https://www.context-awesome.com/api/mcp"
    }
  }
}
{
  "mcpServers": {
    "context-awesome": {
      "url": "https://www.context-awesome.com/api/mcp"
    }
  }
}
  1. Navigate Settings > AI > Manage MCP servers
  2. Click + Add
  3. Configure URL: https://www.context-awesome.com/api/mcp
  4. Click Save
{
  "mcpServers": {
    "context-awesome": {
      "type": "http",
      "url": "https://www.context-awesome.com/api/mcp",
      "tools": ["find_awesome_section", "search_awesome_items", "get_awesome_items"]
    }
  }
}
  1. Navigate to Program > Install > Edit mcp.json
  2. Add:
{
  "mcpServers": {
    "context-awesome": {
      "url": "https://www.context-awesome.com/api/mcp"
    }
  }
}
{
  "mcpServers": {
    "context-awesome": {
      "url": "https://www.context-awesome.com/api/mcp"
    }
  }
}
  1. Navigate Perplexity > Settings
  2. Select Connectors
  3. Click Add Connector
  4. Select Advanced
  5. Enter Name: Context Awesome
  6. Enter URL: https://www.context-awesome.com/api/mcp
{
  "inputs": [],
  "servers": {
    "context-awesome": {
      "type": "http",
      "url": "https://www.context-awesome.com/api/mcp"
    }
  }
}
{
  "$schema": "https://charm.land/crush.json",
  "mcp": {
    "context-awesome": {
      "type": "http",
      "url": "https://www.context-awesome.com/api/mcp"
    }
  }
}
acli rovodev mcp

Then add:

{
  "mcpServers": {
    "context-awesome": {
      "url": "https://www.context-awesome.com/api/mcp"
    }
  }
}
  1. Go to Zencoder menu (...)
  2. Select Agent tools
  3. Click Add custom MCP
  4. Name: Context Awesome
  5. URL: https://www.context-awesome.com/api/mcp
  1. Open Qodo Gen chat panel
  2. Click Connect more tools
  3. Click + Add new MCP
  4. Add:
{
  "mcpServers": {
    "context-awesome": {
      "url": "https://www.context-awesome.com/api/mcp"
    }
  }
}

License

MIT

Contributing

Contributions are welcome! Please:

  1. Fork the repository
  2. Create a feature branch
  3. Add tests for new functionality
  4. Ensure all tests pass
  5. Submit a pull request

Support

For issues and questions:

Attribution

This project uses data from over 8,500 awesome lists on GitHub. See ATTRIBUTION.md for a complete list of all repositories whose data is included.

Credits

Built with:

Ver o original no GitHub

Bom para

Relacionados