Diagnose and fix GitHub Actions workflow failures using the GitHub API.
A Multi-Choice Prompt (MCP) utility for diagnosing and fixing GitHub Actions workflow failures using the GitHub API.
This tool helps users diagnose and fix GitHub Actions workflow failures through a structured decision tree. It uses the GitHub API to fetch workflow run information, analyze failures, and provide actionable solutions.
To install githubworkflowmcp for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @Maxteabag/githubworkflowmcp --client claude
# Clone the repository
git clone https://github.com/yourusername/github-workflow-debugger-mcp.git
cd github-workflow-debugger-mcp
# Install dependencies
npm install
# Build the project
npm run build
# Link the binary for local use
npm link
The GitHub Workflow Debugger MCP is designed to be used with AI assistants that support the Model Context Protocol (MCP). It provides several tools that can be used to diagnose and fix GitHub Actions workflow failures.
To use this tool, you'll need a GitHub Personal Access Token (PAT) with the following permissions:
repo
- Full control of private repositoriesworkflow
- Update GitHub Action workflowsYou must set this token as an environment variable named GITHUB_PERSONAL_ACCESS_TOKEN
.
When using this tool with an MCP-compatible client, you can configure it as follows:
{
"mcpServers": {
"github": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-github"
],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>"
}
}
}
}
Replace <YOUR_TOKEN>
with your GitHub Personal Access Token.
Here's an example of how to use the GitHub Workflow Debugger MCP with an AI assistant:
First, get recent failed workflow runs:
I need to check recent failed workflow runs for my repository "username/repo".
Analyze a specific failed run:
Can you analyze workflow run #123456 and suggest fixes?
View the workflow file:
Show me the content of the workflow file at .github/workflows/main.yml
Update the workflow file with fixes:
Update the workflow file with the suggested fixes.
# Install dependencies
npm install
# Build the project
npm run build
src/index.ts
- Main entry point for the MCP serverbuild/
- Compiled JavaScript filesISC
A secure command-line interface server for the Model Context Protocol (MCP) that allows AI models to interact with a user's terminal.
Executes secure shell commands with configurable directory, shell, and timeout validation.
Automates the setup of new AI-powered MCP server development projects.
A command-line tool to run MCP servers from a single file, with support for automatic dependency resolution, environment setup, and package installation from local or S3 sources.
Enables AI assistants to use a Neo4j knowledge graph for standardized coding workflows, acting as a dynamic instruction manual and project memory.
Run code in secure sandboxes hosted by E2B
A lightweight, LLM-agnostic RESTful proxy that unifies multiple MCP servers under a single API.
An experimental MCP server that uses the ast-grep CLI for code structural search, linting, and rewriting.
A template for deploying a remote, authentication-free MCP server on Cloudflare Workers.
A server for CodeFuse-CGM, a graph-integrated large language model designed for repository-level software engineering tasks.