ghas-mcp-server

ghas-mcp-server

Mirror of

MCP-Mirror

Developer Tools
Visit Server

README

ghas-mcp-server

MCP server to make calls to GHAS for GitHub repositories.

Currently this has the following tools that are supported:

  • list_dependabot_alerts: List all dependabot alerts for a repository
  • list_secret_scanning_alerts: List all secret scanning alerts for a repository
  • list_code_scanning_alerts: List all code scanning alerts for a repository

Make sure to add these three scopes (read only) to the configured PAT and for the correct organization as well!

Install in VS Code and VS Code Insiders

Use the buttons to install the server in your VS Code or VS Code Insiders environment. Make sure to read the link before you trust it! The links go to vscode.dev and insiders.vscode.dev and contain instructions to install the server.

VS Code will let you see the configuration before anything happens:

Screenshot of the configuration in VS Code

<img alt="Install in VS Code" src="https://img.shields.io/badge/VS_Code-VS_Code?style=flat-square&label=Install%20Server&color=0098FF"> <img alt="Install in VS Code Insiders" src="https://img.shields.io/badge/VS_Code_Insiders-VS_Code_Insiders?style=flat-square&label=Install%20Server&color=24bfa5">

Example configuration

Add the configurations below to your MCP config in the editor.

Secure option: use the authenticated GitHub CLI

Instead of storing a Personal Access Token (see next section), you can also use the authenticated GitHub CLI. This will use the credentials you have configured in your GitHub CLI. This is useful when you have the GitHub CLI installed and already authenticated.

To use the GitHub CLI for authentication, follow the steps below:

  • Add "GITHUB_PERSONAL_ACCESS_TOKEN_USE_GHCLI": "true" to your environment variables.
  • Ensure you have the GitHub CLI installed and authenticated by running gh auth login.

Configuration:

{
    "mcp": {
        "inputs": [
        ]
    },
    "servers": {
        "ghas-mcp-server": {
            "command": "npx",
            "args": [
                "-y",
                "@rajbos/ghas-mcp-server"
            ],
            "env": {
                "GITHUB_PERSONAL_ACCESS_TOKEN_USE_GHCLI": "true"
            }
        }
    }
  }

Configuration with a personal access token

For VS Code it would look like this:

{
    "mcp": {
        "inputs": [
            {
                "id": "github_personal_access_token",
                "description": "GitHub Personal Access Token",
                "type": "promptString",
                "password": true
            }
        ]
    },
    "servers": {
        "ghas-mcp-server": {
            "command": "npx",
            "args": [
                "-y",
                "@rajbos/ghas-mcp-server"
            ],
            "env": {
                "GITHUB_PERSONAL_ACCESS_TOKEN": "${input:github_personal_access_token}"
            }
        }
    }
  }

Results

Screenshot of the output inside of VS Code

Contributing

Contributions are welcome! If you have ideas for new tools or improvements, please open an issue or submit a pull request.

Quick Start

# Install dependencies
npm install

# Build the project
npm run build

Project Structure

ghas-mcp-server/
├── src/
│   ├── operations/      # MCP Tools
│   │   └── security.ts
│   └── index.ts         # Server entry point
├── package.json
└── tsconfig.json

Adding Components

The project comes with the GHAS tools in src/operations/security.ts.

Building

  1. Make changes to your tools
  2. Run npm run build to compile
  3. The server will automatically load your tools on startup

Testing the local build

You can test your local build by configuring the locally build version with the following MCP config:

"servers": {
    "ghas-mcp-server": {
        "command": "node",
        "args": [
            "C:/Users/RobBos/Code/Repos/rajbos/ghas-mpc-server/dist/index.js"
        ],
        "env": {
            "GITHUB_PERSONAL_ACCESS_TOKEN_USE_GHCLI": "true"
        }
    }
}

Don't forget to change the path to your local build and build the project first!

Learn More

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
MCP Package Docs Server

MCP Package Docs Server

Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.

Featured
Local
TypeScript
Claude Code MCP

Claude Code MCP

An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.

Featured
Local
JavaScript
@kazuph/mcp-taskmanager

@kazuph/mcp-taskmanager

Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.

Featured
Local
JavaScript
Linear MCP Server

Linear MCP Server

Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.

Featured
JavaScript
mermaid-mcp-server

mermaid-mcp-server

A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.

Featured
JavaScript
Jira-Context-MCP

Jira-Context-MCP

MCP server to provide Jira Tickets information to AI coding agents like Cursor

Featured
TypeScript
Linear MCP Server

Linear MCP Server

A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.

Featured
JavaScript
Sequential Thinking MCP Server

Sequential Thinking MCP Server

This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.

Featured
Python