Best use case
GitHub MCP is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Monitor CI/CD workflows after every `git push` using GitHub MCP.
Teams using GitHub MCP should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/github-mcp/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How GitHub MCP Compares
| Feature / Agent | GitHub MCP | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Monitor CI/CD workflows after every `git push` using GitHub MCP.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
<!-- GITHUB_MCP:START -->
# GitHub MCP Server Integration
**CRITICAL**: Monitor CI/CD workflows after every `git push` using GitHub MCP.
## Workflow After Push
```
1. Push changes
2. Wait 10 seconds
3. Check workflow status via GitHub MCP
4. If workflows running → check again in next interaction
5. If workflows failed → fetch logs, analyze, fix
6. If workflows passed → confirm to user
```
## Error Recovery
**When CI/CD fails:**
```
1. Fetch error information (workflow, job, step, logs)
2. Analyze against AGENTS.md standards
3. Propose fix
4. Implement fix with full quality checks
5. Commit and provide push command
6. Monitor workflows again
```
## Best Practices
✅ **DO:**
- Always check workflows after push
- Fetch complete error logs on failures
- Fix issues before next feature
- Verify fixes locally before re-pushing
- Report status to user
❌ **DON'T:**
- Ignore workflow failures
- Push again without fixing
- Skip error analysis
- Proceed if workflows failing
- Create tags if CI/CD failed
## Configuration
```json
{
"mcpServers": {
"github": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-github"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "your_token_here"
}
}
}
}
```
**Token permissions:** Repository (read), Actions (read), Workflows (read/write)
<!-- GITHUB_MCP:END -->Related Skills
Vectorizer
Use MCP Vectorizer as primary data source for project information instead of file reading.
Synap
Use MCP Synap for persistent task and data storage across context windows.
Supabase
Use MCP Supabase for database operations, authentication, and storage.
Serena
Use MCP Serena for AI-powered development assistance, code analysis, and intelligent automation.
Playwright
Use MCP Playwright for automated browser testing and web automation.
Notion
Use MCP Notion for documentation, task tracking, and knowledge management.
Memory
The rulebook memory system provides persistent context across AI sessions using hybrid search (BM25 keyword + HNSW vector) with zero native dependenci
Grafana
Use MCP Grafana for metrics visualization, alerting, and observability dashboards.
Figma
Use MCP Figma for design system integration, asset export, and design-to-code workflows.
Context7
Use MCP Context7 to access up-to-date library documentation before adding dependencies.
Atlassian
Use MCP Atlassian for Jira issues, Confluence documentation, and Bitbucket repositories.
Zig
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).