context-awesome

v0.1.1

Published

21 days ago

CLI + MCP server for curated awesome-list context

0High
0Medium
0Low

bh-rat

mcp model-context-protocol awesome-lists documentation cli

context-awesome : awesome references for your agents

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 :

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

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

Two Ways to Use Context Awesome

| Mode | Install | Good for | | -------------- | ----------------------------------------------------------------- | -------------------------------------------------------------------------- | | MCP Server | point your agent at the hosted URL or spawn context-awesome-mcp | Claude Desktop, Cursor, Windsurf, VS Code — agents that natively speak MCP | | CLI | npm install -g context-awesome | Scripts, 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.

| Tool | CLI equivalent | What it does | | ---------------------- | ------------------------------------- | -------------------------------------------------------------------- | | find_awesome_section | context-awesome sections <query...> | Discover sections/categories across awesome lists matching a query | | search_awesome_items | context-awesome search <query...> | Full-text search across individual items (tools/libraries/resources) | | get_awesome_items | context-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"
    }
  }
}

Click the hamburger menu
Select Settings
Navigate to Tools
Click + Add MCP
Enter URL: https://www.context-awesome.com/api/mcp
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
  }
}

Go to Settings -> Tools -> AI Assistant -> Model Context Protocol (MCP)
Click + Add
Configure URL: https://www.context-awesome.com/api/mcp
Click OK and Apply

Navigate Kiro > MCP Servers
Click + Add
Configure URL: https://www.context-awesome.com/api/mcp
Click Save

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

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

Navigate Settings > AI > Manage MCP servers
Click + Add
Configure URL: https://www.context-awesome.com/api/mcp
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"]
    }
  }
}

Navigate to Program > Install > Edit mcp.json
Add:

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

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

Navigate Perplexity > Settings
Select Connectors
Click Add Connector
Select Advanced
Enter Name: Context Awesome
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"
    }
  }
}

Go to Zencoder menu (...)
Select Agent tools
Click Add custom MCP
Name: Context Awesome
URL: https://www.context-awesome.com/api/mcp

Open Qodo Gen chat panel
Click Connect more tools
Click + Add new MCP
Add:

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

License

MIT

Contributing

Contributions are welcome! Please:

Fork the repository
Create a feature branch
Add tests for new functionality
Ensure all tests pass
Submit a pull request

Support

For issues and questions:

GitHub Issues: https://github.com/bh-rat/context-awesome/issues

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:

Model Context Protocol SDK
Awesome Lists
Inspired by context7 MCP server patterns