Log inSubmit server
Context Awesome logo

Context Awesome

Searches curated Awesome List sections and items, then returns token-budgeted resources through MCP or CLI.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Context Awesome

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "context-awesome": {
      "command": "npx",
      "args": [
        "-y",
        "context-awesome"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

Context Awesome MCP server connects agents to curated Awesome Lists through section discovery, full-text item search, and token-budgeted retrieval. It uses a hosted backend and can run as a remote MCP endpoint, a local stdio or HTTP server, or a CLI with matching operations. Reach for it when an agent needs developer tools, libraries, learning resources, or other references organized across Awesome Lists rather than a general web search. The repository documents setup for several MCP clients, including Cursor, Claude Desktop, Windsurf, VS Code, and Zed.

Use cases

  • Discover sections for a technical topic
  • Search curated tools and libraries by keyword
  • Retrieve token-budgeted references for an agent
  • Build shell workflows around Awesome List data

Key features

  • Awesome List section discovery
  • Full-text item search
  • Token-budgeted item retrieval
  • Remote, stdio, and HTTP MCP transports
  • Matching CLI commands
  • Raw JSON CLI output

Tools3

What Context Awesome lets your agent do. Expand a tool for its parameters.

Self-reported~62 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

6/6 checks healthy over the last 29d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 15d ago via OSV.dev · context-awesome (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars61Stargazers on the source repository.
npm downloads178Package downloads in the last 30 days.
Last commit4mo agoMost recent push to the default branch.
Tools exposed3Callable tools this server registers over MCP.

How Context Awesome works

What Context Awesome MCP server does

Context Awesome MCP server gives agents access to curated Awesome Lists and the resources grouped inside them. These lists cover tools, libraries, and other references across many technical and non-technical topics. The service is intended for knowledge-work agents, research workflows, learning-resource discovery, and search agents that need structured references.

The repository describes coverage of more than 8,500 Awesome Lists and over one million growing list items. Results come from a backend service that processes the lists. The backend is separate from this repository and is planned to be open-sourced later.

How it works

The MCP interface exposes three operations. find_awesome_section locates list sections or categories related to a query. search_awesome_items performs full-text searches over individual items, such as tools, libraries, and resources. get_awesome_items retrieves entries from a known list and section while applying a token budget.

The hosted MCP endpoint is available at https://www.context-awesome.com/api/mcp. A locally launched server can use stdio transport or HTTP transport. Both the MCP server and the CLI use the same backend, and each MCP operation has a corresponding CLI command: sections, search, or items.

Setup and configuration

For a remote connection, add the hosted MCP URL to a compatible client. Cursor, Claude Desktop, Claude Code, Windsurf, VS Code, Zed, JetBrains, Cline, Roo Code, Gemini CLI, and LM Studio are documented in the repository. The exact configuration format depends on the client.

To run the MCP server locally through stdio, install and invoke the package with npx:

Terminal
npx -y context-awesome-mcp serve --transport stdio

The documented Claude Desktop example supplies CONTEXT_AWESOME_API_HOST=https://api.context-awesome.com. For a local HTTP endpoint, run:

Terminal
npx context-awesome-mcp serve --transport http --port 3001

Clients can then connect to http://localhost:3001/mcp. The CLI is installed separately with npm install -g context-awesome, or run on demand with npx context-awesome. Its backend host and API key can be supplied with --api-host and --api-key, or the corresponding environment variables.

Tools and capabilities

Context Awesome MCP server supports these operations:

  • Discover sections matching a topic or query.
  • Search individual Awesome List items by their text.
  • Retrieve items from a specified list and section within a token budget.
  • Use the same discovery and retrieval functions from shell scripts through the CLI.
  • Emit raw JSON from CLI commands with the --json option.

The CLI examples include searches for rate limiters, vector databases, and graph databases. This makes it suitable for narrowing a broad topic to relevant list sections before fetching the entries needed by an agent.

Limitations and notes

The server relies on a hosted backend for Awesome List processing. The available operations are focused on discovering sections, searching items, and retrieving items; the material does not document write operations, list editing, or arbitrary web crawling.

The repository also provides local-development commands that clone the project, install npm dependencies, build it, and run the CLI or MCP server from the generated files.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Context Awesome

Context Awesome is an MCP server that connects AI agents to curated Awesome Lists and their items. Its main tools discover matching sections, search item text across tools, libraries, and resources, and retrieve entries from a known list and section within a token budget. It uses a hosted backend and also has CLI access.

Install it by adding the hosted MCP URL to a supported client, or run the package locally with npx. The documented remote endpoint is https://www.context-awesome.com/api/mcp. Local options include stdio with `npx -y context-awesome-mcp serve --transport stdio` and HTTP with `--transport http`.

Yes, Context Awesome works with Cursor through its remote MCP configuration. In Cursor, open Settings, Cursor Settings, MCP, and Add new global MCP server, then configure the URL `https://www.context-awesome.com/api/mcp`.

Yes, Context Awesome provides a CLI with section discovery, item search, and item retrieval commands. Install it with `npm install -g context-awesome`, or use `npx context-awesome`. The CLI supports `--json`, `--api-host`, and `--api-key` options.

Related MCP servers

All in Developer Tools All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewContext Awesome AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/context-awesome?style=directory)](https://allmcps.com/mcp/context-awesome)
HTML Embed
<a href="https://allmcps.com/mcp/context-awesome"><img src="https://allmcps.com/api/badge/context-awesome?style=directory" alt="Context Awesome on AllMCPs" /></a>