github-actions-mcp
Analyzes GitHub Actions workflows and performance, helping identify bottlenecks, failures, and optimization opportunities in CI/CD pipelines.
README
GitHub Actions MCP Server
An MCP (Model Context Protocol) server for analyzing GitHub Actions workflows and performance. This tool helps identify bottlenecks, failures, and optimization opportunities in your CI/CD pipelines.
Features
- Workflow Discovery: List all workflows in a repository
- Run Analysis: Get detailed information about workflow runs with filtering
- Performance Analysis: Analyze workflow runs to identify slow jobs and failures
- Timing Details: Get detailed timing information for jobs and steps
Installation
- Clone this repository
- Install dependencies:
bun install - Set up your GitHub token:
cp .env.example .env # Edit .env and add your GitHub token - Build the project:
bun run build
Usage
Running the MCP Server
bun run start
The server communicates via stdio and can be integrated with MCP-compatible clients.
Development
The MCP Inspector provides a web-based interface to test your server:
# First, install dependencies
bun install
bun run dev
This will open a web interface where you can:
- View available tools
- Test tool calls interactively
- See request/response data
- Debug tool schemas
Using with Claude Desktop
To use this MCP server with Claude Desktop, add the following configuration to your Claude Desktop settings:
{
"mcpServers": {
"github-actions": {
"command": "bun",
"args": ["run", "start"],
"cwd": "/path/to/your/github-actions-mcp",
"env": {
"GITHUB_TOKEN": "your_github_token_here"
}
}
}
}
Important Notes:
- Replace
/path/to/your/github-actions-mcpwith the actual path to your project directory - Replace
your_github_token_herewith your actual GitHub personal access token - Make sure Bun is installed and available in your system PATH
- Restart Claude Desktop after making configuration changes
After configuration, Claude Desktop will automatically connect to your MCP server and you'll be able to use commands like:
- "List workflows in my repository owner/repo-name"
- "Analyze the latest failed workflow run for owner/repo-name"
- "Show me timing details for workflow run 123456"
GitHub Token Setup
- Go to GitHub Settings > Developer settings > Personal access tokens
- Generate a new token with the following permissions:
repo(Full control of private repositories)actions:read(Read access to actions and workflows)
- Add the token to your
.envfile
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。