Skip to main content
Glama
context-awesome

context-awesome

by bh-rat

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

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.

Related MCP server: toolradar-mcp

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

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:

Available Tools

2 tools
find_awesome_sectionFind Awesome List SectionAInspect

Discovers sections/categories across awesome lists matching a search query and returns matching sections from awesome lists.

You MUST call this function before 'get_awesome_items' to discover available sections UNLESS the user explicitly provides a githubRepo or listId.

Selection Process:

  1. Analyze the query to understand what type of resources the user is looking for

  2. Return the most relevant matches based on:

    • Name similarity to the query and the awesome lists section

    • Category/section relevance of the awesome lists

    • Number of items in the section

    • Confidence score

Response Format:

  • Returns matching sections of the awesome lists with metadata

  • Includes repository information, item counts, and confidence score

  • Use the githubRepo or listId with relevant sections from results for get_awesome_items

For ambiguous queries, multiple relevant sections will be returned for the user to choose from.

Inputs: query (required), confidence, limit.

get_awesome_itemsGet Awesome List ItemsAInspect

Retrieves items from a specific awesome list or section with token limiting. You must call 'find_awesome_section' first to discover available sections, UNLESS the user explicitly provides a githubRepo or listId.

Inputs: listId, githubRepo, section, subcategory, +2 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: 'find_awesome_section' discovers sections/categories across awesome lists based on a search query, while 'get_awesome_items' retrieves actual items from a specific list or section. There is no overlap in functionality—one is for discovery and the other for retrieval, making them perfectly distinguishable.

    Naming Consistency5/5

    Both tools follow a consistent verb_noun pattern with snake_case: 'find_awesome_section' and 'get_awesome_items'. The naming is predictable and readable, with 'find' and 'get' as appropriate verbs for their respective actions, maintaining uniformity throughout the set.

    Tool Count3/5

    With only 2 tools, the server feels thin for its apparent purpose of interacting with awesome lists. While the tools cover discovery and retrieval, typical operations like creating, updating, or deleting items are missing, suggesting the scope might be limited or incomplete. A count of 2 is borderline for a functional server in this domain.

    Completeness2/5

    The tool surface is significantly incomplete for the domain of awesome list management. It only supports discovery and retrieval, lacking any CRUD operations such as adding, updating, or removing items or sections. This will likely cause agent failures when full lifecycle management is needed, as there are obvious gaps in coverage.

    Maintenance

    ActivityInactive
    ResponsivenessMixed handling

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      Not graded
      maintenance
      Search and discover 500+ tools, APIs, and services for AI agents. Browse 15 categories, get recommendations, and access structured metadata including auth methods, free tiers, and example calls.
      1
      -
    • A
      license
      A
      quality
      B
      maintenance
      Give your AI agent access to 8,400+ software tools — search, compare, get pricing, find alternatives, and discover the best tool for any use case.
      11
      95 npm
      4
      MIT
    • F
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to search and retrieve market signals, revenue ideas, and growth tactics from 2,000+ curated entries across 18 sources.
      -
    • A
      license
      A
      quality
      D
      maintenance
      Enables AI agents to search and browse a curated directory of AI projects, including MCP servers, CLI tools, libraries, and APIs, and submit new projects directly from the terminal.
      7
      72 npm
      1
      MIT