mcp-server-github-actions

mcp-server-github-actions

MCP server for GitHub Actions — view workflow runs, read logs, re-run failed jobs, and manage CI/CD.

Category
Visit Server

README

mcp-server-github-actions

npm version npm downloads CI TypeScript License: MIT

Manage GitHub Actions workflows from your AI assistant. List runs, read logs, re-run failed jobs, cancel builds, and trigger deployments without leaving your editor.

npx mcp-server-github-actions

Works with Claude Desktop, Cursor, VS Code Copilot, and any MCP client. Requires a GitHub token with Actions permissions.

MCP server for GitHub Actions workflows, CI/CD runs, and deployment logs

<sub>Demo built with <a href="https://github.com/ofershap/remotion-readme-kit">remotion-readme-kit</a></sub>

Why

GitHub's official MCP server covers repos, issues, and PRs, but it doesn't touch Actions. That means when your CI fails, you still have to open a browser, find the run, click through to the logs, and figure out what went wrong. This server fills that gap. You can ask your assistant "why did the last CI run fail?" or "re-run the failed jobs" and get answers right where you're working. It uses the same GitHub REST API you'd use manually, just without the context switching.

Tools

Tool Description
list_workflows List all workflow files in a repository
list_runs List workflow runs (optionally 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 file 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

Quick Start

Cursor

Add to your Cursor MCP settings (e.g. ~/.cursor/mcp.json or project-level):

{
  "mcpServers": {
    "github-actions": {
      "command": "npx",
      "args": ["-y", "mcp-server-github-actions"],
      "env": {
        "GITHUB_TOKEN": "<your-token>"
      }
    }
  }
}

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "github-actions": {
      "command": "npx",
      "args": ["-y", "mcp-server-github-actions"],
      "env": {
        "GITHUB_TOKEN": "<your-token>"
      }
    }
  }
}

VS Code

Configure your MCP client to run:

npx mcp-server-github-actions

Make sure GITHUB_TOKEN is set in the environment (e.g. in your shell profile or client config).

Auth

Create a GitHub Personal Access Token:

  1. Settings > Developer settings > Personal access tokens
  2. Choose Fine-grained tokens (recommended) or Tokens (classic)
  3. Fine-grained: select your repos, then enable Actions: Read and Write
  4. Classic: enable the repo scope (includes Actions)

Example Prompts

  • "List the last 5 workflow runs for ofershap/mcp-server-docker"
  • "Show me the workflows in the microsoft/vscode repo"
  • "Get details for run 12345 in owner/repo"
  • "Re-run the failed jobs for run 67890 in my-org/my-repo"
  • "Cancel the currently running workflow run 11111"
  • "List artifacts from the latest run in owner/repo"
  • "Trigger the deploy.yml workflow on the staging branch for my-org/my-app"
  • "What's the status of the most recent CI run for this project?"

Development

npm install
npm run typecheck
npm run build
npm test
npm run lint
npm run format

See also

More MCP servers and developer tools on my portfolio.

Author

Made by ofershap

LinkedIn GitHub


<sub>README built with README Builder</sub>

License

MIT © 2026 Ofer Shapira

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured