MCP Servers Search
Enables discovery and querying of available MCP servers from the official repository. Supports searching by name, description, features, categories, and provides random server suggestions for exploration.
README
MCP Servers Search
An MCP (Model Context Protocol) server that provides tools for querying and discovering available MCP servers from the official modelcontextprotocol/servers repository.
547 MCP servers as of June 2025.
Features
- List Servers: Browse all available MCP servers with filtering by category
- Search: Find servers by name, description, or author
- Feature Search: Discover servers that provide specific capabilities
- Random Discovery: Get random server suggestions for exploration
- Caching: Efficient caching to minimize GitHub API calls
Installation
Using npm
npm install -g @atonomus/mcp-servers-search
From source
git clone https://github.com/atonomus/mcp-servers-search.git
cd mcp-servers-search
npm install
Usage
Standalone
# Run directly with npx
npx @atonomus/mcp-servers-search
# Or if installed globally
mcp-servers-search
With Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"servers-search": {
"command": "npx",
"args": ["-y", "@atonomus/mcp-servers-search"]
}
}
}
Available Tools
1. list_servers
List all available MCP servers with optional filtering.
Parameters:
category(optional): Filter by category - "reference", "official", "community", or "all" (default)search(optional): Search servers by name or descriptionlimit(optional): Maximum number of results (default: 20)
Example:
{
"name": "list_servers",
"arguments": {
"category": "official",
"search": "database",
"limit": 10
}
}
2. get_server_details
Get detailed information about a specific MCP server.
Parameters:
name(required): The name of the MCP server
Example:
{
"name": "get_server_details",
"arguments": {
"name": "GitHub"
}
}
3. search_servers_by_feature
Search for servers that provide specific features or capabilities.
Parameters:
feature(required): The feature to search for (e.g., "database", "api", "blockchain")limit(optional): Maximum number of results (default: 10)
Example:
{
"name": "search_servers_by_feature",
"arguments": {
"feature": "blockchain",
"limit": 5
}
}
4. get_random_servers
Get a random selection of MCP servers for discovery.
Parameters:
count(optional): Number of random servers (default: 5)category(optional): Filter by category (default: "all")
Example:
{
"name": "get_random_servers",
"arguments": {
"count": 3,
"category": "community"
}
}
5. refresh_server_list
Force refresh the cached list of MCP servers from GitHub.
Example:
{
"name": "refresh_server_list",
"arguments": {}
}
Development
Setup
# Install dependencies
npm install
# Run normally
npm start
# Run tests
npm test
Testing
The project includes a comprehensive Mocha test suite that tests the README parsing functionality. The tests cover:
- Standard format entries:
[Name](link) - description - Bold format entries:
**[Name](link)** - description - List format entries:
- [Name](link) - description - Author extraction:
(by AuthorName) - Category detection (reference, official, community)
- Description cleaning (removing embedded links)
- Special character handling (preserving backticks)
Run tests with:
npm test
Examples
Using with Claude Desktop
Once configured, you can ask Claude:
- "What MCP servers are available for database operations?"
- "Show me all official MCP servers"
- "Find MCP servers related to AI or machine learning"
- "Give me 5 random community servers to explore"
- "Tell me more about the GitHub MCP server"
Programmatic Usage
// Example of using the server programmatically
import { MCPToolsQueryServer } from '@atonomus/mcp-servers-search';
const server = new MCPToolsQueryServer();
await server.run();
Caching
The server caches the list of available MCP servers for 1 hour to minimize API calls to GitHub. You can force a refresh using the refresh_server_list tool.
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
License
MIT - see LICENSE file for details
Acknowledgments
- Built on the Model Context Protocol SDK
- Data sourced from the official MCP Servers Repository
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。