MCP 服务器

context-awesome

Give your AI agents access to 8,500+ community curated awesome lists with over 1 million curated resources.

README

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

Available Tools

1. `find_awesome_section`

Discovers sections and categories across awesome lists matching your search query.

Parameters:

query (required): Search terms for finding sections
confidence (optional): Minimum confidence score (0-1, default: 0.3)
limit (optional): Maximum sections to return (1-50, default: 10)

Example Usage: "Give me the best machine learning resources for learning ML related to python in couple of months." "What are the best resources for authoring technical books ?" "Find awesome list sections about React hooks" "Search for database ORMs in Go awesome lists"

2. `get_awesome_items`

Retrieves items from a specific list or section with token limiting for optimal context usage.

Parameters:

listId or githubRepo (one required): Identifier for the list
section (optional): Category/section name to filter
subcategory (optional): Subcategory to filter
tokens (optional): Maximum tokens to return (min: 1000, default: 10000)
offset (optional): Pagination offset (default: 0)

Example Usage:

"Show me the testing tools section from awesome-rust"
"Get the next 20 items from awesome-python (offset: 20)"
"Get items from bh-rat/awesome-mcp-enterprise"

Installation

Remote Server (Recommended)

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

<details> <summary>Install in Cursor</summary>

Go to: Settings -> Cursor Settings -> MCP -> Add new global MCP server

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

</details>

<details> <summary>Install in Claude Code</summary>

claude mcp add --transport http context-awesome https://www.context-awesome.com/api/mcp

</details>

<details> <summary>Install in Windsurf</summary>

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

</details>

<details> <summary>Install in VS Code</summary>

"mcp": {
  "servers": {
    "context-awesome": {
      "type": "http",
      "url": "https://www.context-awesome.com/api/mcp"
    }
  }
}

</details>

<details> <summary>Install in Claude Desktop</summary>

Navigate to Settings > Connectors > Add Custom Connector. Enter:

Name: Context Awesome
URL: https://www.context-awesome.com/api/mcp </details>

See Additional Installation Methods for other MCP clients.

Local Setup

For development or self-hosting:

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

Configuration

Running the Server

# Development mode (runs from source)
npm run dev -- [options]

# Production mode (runs compiled version)
npm run start -- [options]

Options:
  --transport <stdio|http|sse>  Transport mechanism (default: stdio)
  --port <number>               Port for HTTP transport (default: 3000)
  --api-host <url>             Backend API host (default: https://api.context-awesome.com)
  --debug                      Enable debug logging
  --help                       Show help

Examples

# Run with default settings (stdio transport)
npm run start

# Run with HTTP transport on port 3001
npm run start -- --transport http --port 3001

# Run with custom API host and key
npm run start -- --api-host https://api.context-awesome.com

MCP Client Configuration

<details> <summary>Claude Desktop</summary>

Add to your Claude Desktop configuration file:

{
  "mcpServers": {
    "context-awesome": {
      "command": "node",
      "args": ["/path/to/context-awesome/build/index.js"],
      "env": {
        "CONTEXT_AWESOME_API_HOST": "https://api.context-awesome.com"
      }
    }
  }
}

</details>

<details> <summary>Cursor/VS Code</summary>

Add to your settings:

{
  "mcpServers": {
    "context-awesome": {
      "command": "node",
      "args": ["/path/to/context-awesome/build/index.js"],
      "env": {
        "CONTEXT_AWESOME_API_HOST": "https://api.context-awesome.com"
      }
    }
  }
}

</details>

<details> <summary>Custom Integration</summary>

For HTTP transport:

npm run start -- --transport http --port 3001 --api-host https://api.context-awesome.com

Then configure your client to connect to http://localhost:3001/mcp </details>

Testing

With MCP Inspector

npm run inspector

Debug Mode

Enable debug logging to see detailed information:

npm run start -- --debug

# Or in development mode
npm run dev -- --debug

Additional Installation Methods

<details> <summary>Install in Cline</summary>

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

</details>

<details> <summary>Install in Zed</summary>

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

</details>

<details> <summary>Install in Augment Code</summary>

Click the hamburger menu
Select Settings
Navigate to Tools
Click + Add MCP
Enter URL: https://www.context-awesome.com/api/mcp
Name: Context Awesome </details>

<details> <summary>Install in Roo Code</summary>

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

</details>

<details> <summary>Install in Gemini CLI</summary>

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

</details>

<details> <summary>Install in Opencode</summary>

"mcp": {
  "context-awesome": {
    "type": "remote",
    "url": "https://www.context-awesome.com/api/mcp",
    "enabled": true
  }
}

</details>

<details> <summary>Install in JetBrains AI Assistant</summary>

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 </details>

<details> <summary>Install in Kiro</summary>

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

<details> <summary>Install in Trae</summary>

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

</details>

<details> <summary>Install in Amazon Q Developer CLI</summary>

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

</details>

<details> <summary>Install in Warp</summary>

Navigate Settings > AI > Manage MCP servers
Click + Add
Configure URL: https://www.context-awesome.com/api/mcp
Click Save </details>

<details> <summary>Install in Copilot Coding Agent</summary>

{
  "mcpServers": {
    "context-awesome": {
      "type": "http",
      "url": "https://www.context-awesome.com/api/mcp",
      "tools": ["find_awesome_section", "get_awesome_items"]
    }
  }
}

</details>

<details> <summary>Install in LM Studio</summary>

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

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

</details>

<details> <summary>Install in BoltAI</summary>

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

</details>

<details> <summary>Install in Perplexity Desktop</summary>

Navigate Perplexity > Settings
Select Connectors
Click Add Connector
Select Advanced
Enter Name: Context Awesome
Enter URL: https://www.context-awesome.com/api/mcp </details>

<details> <summary>Install in Visual Studio 2022</summary>

{
  "inputs": [],
  "servers": {
    "context-awesome": {
      "type": "http",
      "url": "https://www.context-awesome.com/api/mcp"
    }
  }
}

</details>

<details> <summary>Install in Crush</summary>

{
  "$schema": "https://charm.land/crush.json",
  "mcp": {
    "context-awesome": {
      "type": "http",
      "url": "https://www.context-awesome.com/api/mcp"
    }
  }
}

</details>

<details> <summary>Install in Rovo Dev CLI</summary>

acli rovodev mcp

Then add:

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

</details>

<details> <summary>Install in Zencoder</summary>

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

<details> <summary>Install in Qodo Gen</summary>

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"
    }
  }
}

</details>

Backend service

This MCP server connects 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.

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/your-org/context-awesome/issues
Documentation: https://docs.context-awesome.com

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

context-awesome

README

context-awesome : awesome references for your agents

Available Tools

1. find_awesome_section

2. get_awesome_items

Installation

Remote Server (Recommended)

Local Setup

Configuration

Running the Server

Examples

MCP Client Configuration

Testing

With MCP Inspector

Debug Mode

Additional Installation Methods

Backend service

License

Contributing

Support

Attribution

Credits

推荐服务器

1. `find_awesome_section`

2. `get_awesome_items`