Which integrations are available for this server?

Searches GitHub repositories for similar issues based on issue descriptions, calculates similarity scores, and returns formatted issue details with links to help support engineers speed up troubleshooting.

How do I use GitHub Support Assistant?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@GitHub Support Assistant find similar issues to 'login fails after password reset' in facebook/react" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

GitHub Support Assistant

An MCP server that helps support engineers find similar GitHub issues to speed up troubleshooting.

Setup

Install dependencies:

npm install

Set your GitHub token as an environment variable:

export GITHUB_TOKEN=your_github_personal_access_token

Build the server:

npm run build

Integrating with Claude:

Update the claude desktop configuration, e.g. code ~/Library/Application\ Support/Claude/claude_desktop_config.json

Update it to include the full path that this repository was cloned to:

{
    "mcpServers": {
        "find-similar-github-issues": {
            "command": "node",
            "args": [
                "/Users/<repo_path>/build/index.js"
            ]
        }
    }
}

Related MCP server: OSSInsight MCP Server

Features

Searches for similar issues in a GitHub repository based on issue description
Calculates similarity scores to rank results
Returns formatted issue details with links

Usage

The server provides one tool:

find-similar-issues

Finds GitHub issues similar to a given description.

Parameters:

owner: GitHub repository owner/organization
repo: GitHub repository name
issueDescription: Description of the issue to find similar ones for
maxResults: Maximum number of similar issues to return (default: 5)

Implementation Notes

This implementation uses a simple Jaccard similarity coefficient to compare text. For production use, consider implementing more sophisticated NLP techniques for better similarity matching.