Context Awesome

io.github.bh-rat由 GitHub 账号 bh-rat 发布v0.1.1更新于 Oct 24, 2026

MCP server for accessing curated awesome list documentation

发布方自己的服务：Awesome Tools

已验证Streamable HTTP可网页运行网页搜索与抓取知识与记忆

概览

AI 生成的概览

搜索 GitHub 上社区精选的 awesome 列表，返回匹配的章节与资源条目，供助手引用。

可以做什么
  • 按查询在数千个 awesome 列表中查找匹配的章节与分类
  • 从已知列表或章节获取条目（工具、库、资源），并受 token 上限约束
  • 在用户提供 GitHub 仓库或列表 ID 时直接按该目标查询
  • 同样的操作也以命令行工具形式提供，便于脚本与 CI 使用
适用场景
适合希望助手推荐经过筛选的优质资源、而不是依赖普通网页搜索的场景，例如深度调研、学习资源汇总或参考资料收集。
运行要求
可使用托管远程端点（无需安装），或用 npx 从 context-awesome-mcp 包启动本地进程（需要 Node.js）。本地模式可设置 CONTEXT_AWESOME_API_HOST；命令行工具还支持 CONTEXT_AWESOME_API_KEY。需要能访问托管后端。
安装前请注意
查询内容会发送到第三方托管后端，搜索词会离开本机。后端尚未开源。命令行工具文档提到可通过 CONTEXT_AWESOME_API_KEY 提供 API 密钥，应按机密信息对待。这些工具只读取数据。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Context Awesome，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.bh-rat%2Fcontext-awesome/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "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:

来源：README.md，提交 7ed2de1

工具

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.

输入参数limitquery必填confidence

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.

输入参数listIdoffsettokenssectiongithubReposubcategory

版本历史

1
  1. v0.1.1最新Sep 16, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Awesome 集成

Awesome Tools

tools.awesome官方发布者

搜索精选的 SaaS 与 AI 工具目录，查看分类与标签，提交自己的产品，并验证回链徽章。

Streamable HTTP可网页运行
网页搜索与抓取7 个工具Nov 7, 2026

Awesome JEV

由 GitHub 账号 daftAI2026 发布

搜索 Jev / System One 项目并查看其记录的纳入证据。AI 翻译

Streamable HTTP可网页运行
2 个工具Oct 25, 2026

Awesome Report

由 GitHub 账号 ks0430 发布

让助手把调查结果发布成包含表格、图表和图解的整洁网页，并提供一个可分享的链接。

Streamable HTTP可网页运行鉴权
效率与工作流需要凭据Oct 24, 2026

Awesome Agent Skills

由 GitHub 账号 shadowrootdev 发布

一个本地 MCP 服务器，为助手提供 100 多个精选 AI 智能体技能目录，可列出、查看、调用和刷新这些技能。

STDIO仅桌面
知识与记忆尚未验证Oct 24, 2026

Awesome Copilot MCP Server

由 GitHub 账号 microsoft 发布

一个本地 MCP 服务器，从 Awesome Copilot 仓库获取 GitHub Copilot 自定义文件，供助手使用。

STDIO仅桌面
知识与记忆未验证 · 该软件包类型无法在沙箱中运行Nov 4, 2026