
Github Actions Management
- 1 installs
- 4 repo stars
- Updated March 10, 2026
- ofershap/mcp-server-github-actions
Manages GitHub Actions over MCP: list workflows and runs, inspect run details, re-run failed jobs, cancel runs, and trigger workflow_dispatch.
About
This skill provides MCP tools to check CI status, read run details, re-run failed jobs, cancel runs, list artifacts, and trigger workflows on GitHub Actions. A developer uses it to monitor and manage CI/CD pipelines.
- Prefers rerun_failed_jobs to save compute
- trigger_workflow requires a workflow_dispatch trigger
Github Actions Management by the numbers
- 1 all-time installs (skills.sh)
- Ranked #1,173 of 1,435 DevOps & CI/CD skills by installs in the Skillselion catalog
- Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ofershap/mcp-server-github-actions --skill github-actions-managementAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| repo stars | ★ 4 |
| Last updated | March 10, 2026 |
| Repository | ofershap/mcp-server-github-actions ↗ |
What it does
Manages GitHub Actions over MCP: list workflows and runs, inspect run details, re-run failed jobs, cancel runs, and trigger workflow_dispatch.
Files
GitHub Actions Management via MCP
Use this skill when you need to check CI/CD status, read workflow logs, re-run failed jobs, or trigger deployments.
Available Tools
| Tool | What it does |
|---|---|
list_workflows | List all workflow files in a repository |
list_runs | List workflow runs (filter by workflow or status) |
get_run | Get details of a specific workflow run |
get_run_logs | Get the logs URL for a run (zip download) |
rerun_workflow | Re-run an entire workflow run |
rerun_failed_jobs | Re-run only the failed jobs from a run |
cancel_run | Cancel an in-progress or queued run |
list_artifacts | List artifacts produced by a workflow run |
trigger_workflow | Trigger a workflow via workflow_dispatch |
Workflow
1. Use list_runs with owner and repo to see recent runs and their status 2. For failed runs: get_run for details, then decide whether to rerun_failed_jobs or investigate logs 3. trigger_workflow requires the workflow file name and a branch — the workflow must have a workflow_dispatch trigger
Key Patterns
- All tools require
ownerandrepoparameters (e.g.,owner: "ofershap",repo: "my-project") list_runssupportsstatusfilter: "completed", "in_progress", "queued", "failure", "success"rerun_failed_jobsis preferred overrerun_workflow— it's faster and cheapertrigger_workflowneedsworkflow_id(filename like "ci.yml") andref(branch name)
Safety
- Prefer
rerun_failed_jobsover fullrerun_workflowto avoid unnecessary compute - Confirm before
cancel_run— the user may want the run to finish trigger_workflowcan trigger deployments — always confirm the target branch