Context Awesome

io.github.bh-ratPublished by GitHub account bh-ratv0.1.1Updated Oct 24, 2026

MCP server for accessing curated awesome list documentation

The publisher's own server: Awesome Tools

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Searches community-curated GitHub awesome lists and returns matching sections and resource items for an assistant to cite.

What you can do
  • Find sections and categories across thousands of awesome lists that match a query
  • Fetch the items (tools, libraries, resources) from a known list or section, with token limits
  • Look up curated references by GitHub repo or list ID when the user supplies one
  • Same operations are also exposed as a command-line tool for scripts and CI
When to use it
Useful when an assistant should recommend vetted, curated resources on a topic instead of relying on generic web search, for research, learning-resource roundups, or reference gathering.
Requirements
Either the hosted remote endpoint (no install) or a local process started with npx from the context-awesome-mcp package, which needs Node.js. The local mode can set CONTEXT_AWESOME_API_HOST; the CLI also accepts CONTEXT_AWESOME_API_KEY. Network access to the hosted backend is required.
Before you install
Queries and lookups are sent to the third-party hosted backend, so search terms leave the user's machine. The backend is not yet open source. The CLI documents an optional API key via CONTEXT_AWESOME_API_KEY; treat it as a secret. The tools are read-only.

Installation

In SourceWeft

  1. Open Context Awesome in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.bh-rat%2Fcontext-awesome/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

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

README

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

bash
npm install -g context-awesomecontext-awesome --helpcontext-awesome search "rate limiter"context-awesome sections "graph databases"

Use the CLI without installing

bash
npx context-awesome search "vector database"

Installation — MCP Clients

Remote Server (Recommended)

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

Install in Cursor

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

json
{  "mcpServers": {    "context-awesome": {      "url": "https://www.context-awesome.com/api/mcp"    }  }}
Install in Claude Code
sh
claude mcp add --transport http context-awesome https://www.context-awesome.com/api/mcp
Install in Claude Desktop

Settings → Connectors → Add Custom Connector.

  • Name: Context Awesome
  • URL: https://www.context-awesome.com/api/mcp
Install in Windsurf / VS Code / Zed / JetBrains / LM Studio / ...

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)

json
{  "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)

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

Local Development

bash
git clone https://github.com/bh-rat/context-awesome.gitcd context-awesomenpm installnpm run build
# CLI./build/cli.js search "graph databases"
# MCP server (stdio)./build/index.js --transport stdio
# MCP Inspectornpm 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

Install in Cline
json
{  "mcpServers": {    "context-awesome": {      "url": "https://www.context-awesome.com/api/mcp"    }  }}
Install in Zed
json
{  "context_servers": {    "context-awesome": {      "url": "https://www.context-awesome.com/api/mcp"    }  }}
Install in Augment Code
  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
Install in Roo Code
json
{  "mcpServers": {    "context-awesome": {      "type": "streamable-http",      "url": "https://www.context-awesome.com/api/mcp"    }  }}
Install in Gemini CLI
json
{  "mcpServers": {    "context-awesome": {      "httpUrl": "https://www.context-awesome.com/api/mcp"    }  }}
Install in Opencode
json
"mcp": {  "context-awesome": {    "type": "remote",    "url": "https://www.context-awesome.com/api/mcp",    "enabled": true  }}
Install in JetBrains AI Assistant
  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
Install in Kiro
  1. Navigate Kiro > MCP Servers
  2. Click + Add
  3. Configure URL: https://www.context-awesome.com/api/mcp
  4. Click Save
Install in Trae
json
{  "mcpServers": {    "context-awesome": {      "url": "https://www.context-awesome.com/api/mcp"    }  }}
Install in Amazon Q Developer CLI
json
{  "mcpServers": {    "context-awesome": {      "url": "https://www.context-awesome.com/api/mcp"    }  }}
Install in Warp
  1. Navigate Settings > AI > Manage MCP servers
  2. Click + Add
  3. Configure URL: https://www.context-awesome.com/api/mcp
  4. Click Save
Install in Copilot Coding Agent
json
{  "mcpServers": {    "context-awesome": {      "type": "http",      "url": "https://www.context-awesome.com/api/mcp",      "tools": ["find_awesome_section", "search_awesome_items", "get_awesome_items"]    }  }}
Install in LM Studio
  1. Navigate to Program > Install > Edit mcp.json
  2. Add:
json
{  "mcpServers": {    "context-awesome": {      "url": "https://www.context-awesome.com/api/mcp"    }  }}
Install in BoltAI
json
{  "mcpServers": {    "context-awesome": {      "url": "https://www.context-awesome.com/api/mcp"    }  }}
Install in Perplexity Desktop
  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
Install in Visual Studio 2022
json
{  "inputs": [],  "servers": {    "context-awesome": {      "type": "http",      "url": "https://www.context-awesome.com/api/mcp"    }  }}
Install in Crush
json
{  "$schema": "https://charm.land/crush.json",  "mcp": {    "context-awesome": {      "type": "http",      "url": "https://www.context-awesome.com/api/mcp"    }  }}
Install in Rovo Dev CLI
bash
acli rovodev mcp

Then add:

json
{  "mcpServers": {    "context-awesome": {      "url": "https://www.context-awesome.com/api/mcp"    }  }}
Install in Zencoder
  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
Install in Qodo Gen
  1. Open Qodo Gen chat panel
  2. Click Connect more tools
  3. Click + Add new MCP
  4. Add:
json
{  "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:

Source: README.md at commit 7ed2de1

Tools

2

find_awesome_section

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.

Parameterslimitqueryrequiredconfidence

get_awesome_items

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.

ParameterslistIdoffsettokenssectiongithubReposubcategory

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Awesome integrations

Awesome Tools

tools.awesomeOfficial publisher

Search a curated directory of SaaS and AI tools, read categories and tags, submit your own product, and verify a backlink badge.

Streamable HTTPWeb executable
Web Search & Scraping7 toolsNov 7, 2026

Awesome JEV

Published by GitHub account daftAI2026

Awesome JEV's hosted MCP server; no sign-in required; Streamable HTTP; 2 tools.

Streamable HTTPWeb executable
2 toolsOct 25, 2026

Awesome Report

Published by GitHub account ks0430

Lets an assistant publish its findings as a clean, shareable web page with tables, charts and diagrams.

Streamable HTTPWeb executableAuth
Productivity & WorkflowCredential requiredOct 24, 2026

Awesome Agent Skills

Published by GitHub account shadowrootdev

A local MCP server that gives an assistant a catalog of 100+ curated AI agent skills, letting it list, inspect, invoke and refresh them.

STDIODesktop only
Knowledge & MemoryNot validated yetOct 24, 2026

Awesome Copilot MCP Server

Published by GitHub account microsoft

A local MCP server that retrieves GitHub Copilot customization files from the Awesome Copilot repository for use in an assistant.

STDIODesktop only
Knowledge & MemoryNot validated · the package type cannot run in the sandboxNov 4, 2026