MCP server · Developer tools

GitHub Actions MCP server

Lets your AI check, re-run, cancel, and trigger GitHub Actions workflow runs for you.

Developer tools For it and development Developer Tools

This is a small helper that connects your AI assistant to GitHub Actions, the part of GitHub that runs your automated builds and tests. Once it is set up, you can ask your AI things like why the last build failed, or to re-run the jobs that broke, without opening a browser tab. It is handy for anyone who pushes code and watches those little green and red check marks.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to an app or service. This one connects your AI to GitHub Actions, so when you ask about a build or a workflow run, the AI can actually go look it up or act on it for you. You set it up once, and after that it just works in the background.

What this MCP server does

You ask your AI a question about your GitHub Actions builds, like whether the last run passed or why it failed. The AI passes that request to this helper, which talks to GitHub on your behalf using a token you provide. GitHub sends back the details, like the list of runs, the run status, or a link to the log files. The AI then explains it to you in plain words, right in the chat. If you ask it to, it can also re-run jobs, cancel a run, or start a workflow.

Flow diagram: you ask your AI “Did my latest build pass?”, the GitHub Actions MCP server connects it to GitHub Actions, and you get back A plain answer in your chat.

Click to zoom

What you can do with it

List the workflows in a repository
List recent workflow runs and their statuses
Get the details of one specific run
Get a download link for a run's log files
Re-run an entire workflow run
Re-run only the jobs that failed
Cancel a run that is still going
List the artifacts a run produced

Try asking your AI

“What's the status of the most recent CI run for this project?”
“Why did the last workflow run fail in owner/repo?”
“Re-run the failed jobs for run 67890 in my-org/my-repo”
“Cancel the currently running workflow run 11111”
“Trigger the deploy.yml workflow on the staging branch for my-org/my-app”

What it gives back to you

You get answers in the chat: lists of runs with their statuses, details about a single run, or a link to download the log files as a zip. When you ask it to re-run, cancel, or trigger something, it tells you that the action was done. It does not dump raw log text into the chat, it gives you the link so you can open the logs yourself.

Before you start

What you need

A GitHub account with access to the repositories you want to manage
A GitHub personal access token with Actions read and write permission (a kind of password for apps; GitHub lets you create one in your settings)
Node.js installed on your computer, since the server runs with npx
An MCP client like Claude Desktop, Cursor, or VS Code Copilot

Good to know

It can re-run, cancel, and trigger workflows on your repositories, so make sure your token only has access to the repos you are comfortable with.

Install it with your AI

Add GitHub Actions MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check GitHub Actions MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.