home / mcp / github actions mcp server
GitHub Actions Model Context Protocol Server
Configuration
View docs{
"mcpServers": {
"ko1ynnky-github-actions-mcp-server": {
"command": "node",
"args": [
"<path-to-mcp-server>/dist/index.js"
],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>"
}
}
}
}You can run the GitHub Actions MCP Server locally and connect it to your AI coding assistants. It exposes a set of actions to list, view, trigger, and monitor GitHub Actions workflows, with safeguards for security and robust input handling so your automation can operate reliably across repositories.
To use this MCP server with an AI coding assistant, run the local MCP server process and point your assistant’s MCP client to it. The server is designed to be started as a local stdio process, typically via node and the built dist/index.js file. Your assistant will then be able to call actions such as listing workflows, triggering runs, and inspecting workflow details.
Prerequisites you need on your machine before starting:
Install and build the MCP server locally:
# Clone the MCP server repository
git clone https://github.com/ko1ynnky/github-actions-mcp-server.git
cd github-actions-mcp-server
# Install dependencies
npm install
# Build the project
npm run buildStart the MCP server locally using the standard runtime command shown in the configurations below. You will typically run the server as a stdio process with Node, pointing to the built entry file.
{
"mcpServers": {
"github_actions": {
"command": "node",
"args": [
"<path-to-mcp-server>/dist/index.js"
],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>"
}
}
}
}List workflows in a GitHub repository. Requires owner and repo; supports optional pagination.
Retrieve detailed information about a specific workflow by ID or filename.
Fetch usage statistics for a workflow, including billable minutes.
List all workflow runs for a repository or a specific workflow with multiple filters (actor, branch, event, status, date, etc.).
Get details for a specific workflow run by runId.
Retrieve the jobs associated with a particular workflow run, with optional pagination and filtering.
Trigger a workflow run on a specified ref with optional inputs.
Cancel a running workflow by runId.
Re-run a previously triggered workflow run by runId.