MCP Server
Allows accessing resources and prompts from a GitHub repository, enabling sharing of coding standards, documentation, and reusable prompts across a team.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Serverlist available prompts from my team's repo"
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.
MCP Server
A Model Context Protocol (MCP) server that provides access to resources and prompts from different repository sources. This allows you to share coding standards, documentation, and reusable prompts across your team by storing them in a GitHub repository, making them accessible to Claude and other MCP-compatible AI tools.
Quick Start
The fastest way to get started is using a GitHub repository. First, create a repository with this structure:
your-repo/
├── index.json
├── resources/
│ └── your-resource.md
└── prompts/
└── your-prompt.mdCreate an index.json file that declares what resources and prompts are available:
{
"resources": [
{
"name": "your-resource",
"description": "Description of your resource"
}
],
"prompts": [
{
"name": "your-prompt",
"description": "Description of your prompt"
}
]
}Add this to your Claude configuration:
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"--yes",
"github:cressie176/mcp-server",
"--repository-type", "github",
"--user", "your-username",
"--repository", "your-repo"
]
}
}
}Restart Claude and your resources and prompts will be available. You can confirm using the /mcp command.
See my prompts repository for examples.
Related MCP server: code2prompt-mcp
Usage
GitHub Repository
Access resources and prompts from a GitHub repository:
npx --yes github:cressie176/mcp-server --repository-type github --user your-user --repository your-repoGitHub Options:
--user: GitHub username--organisation: GitHub organisation name--repository: Repository name--ref: Git reference (default:heads/main)--path: Path within the repository (optional)--log-level: Logging level (debug, info, warn, error, off)--log-file: Log file path (default: debug.log)
Local File System
Access resources and prompts from a local directory (useful for testing):
npx --yes github:cressie176/mcp-server --repository-type filesystem --path ./path/to/folderFile System Options:
--path: Path to the directory containing your resources and prompts--log-level: Logging level (debug, info, warn, error, off)--log-file: Log file path (default: debug.log)
Repository Structure
Your repository (whether GitHub or local file system) should follow this structure:
├── index.json # Defines available resources and prompts
├── resources/ # Directory containing resource files
│ └── *.md # Markdown resource files
└── prompts/ # Directory containing prompt files
└── *.md # Markdown prompt filesindex.json Format
{
"resources": [
{
"name": "code-standards",
"description": "Coding standards and guidelines"
}
],
"prompts": [
{
"name": "code-review",
"description": "Perform a comprehensive code review"
}
]
}Claude Configuration
GitHub repositories:
{
"mcpServers": {
"your-server-name": {
"command": "npx",
"args": [
"--yes",
"github:cressie176/mcp-server"
"--repository-type", "github",
"--user", "your-username",
"--repository", "your-repo"
]
}
}
}FileSystem Repositories
Add the following to your claude configuration file:
{
"mcpServers": {
"your-server-name": {
"command": "npx",
"args": [
"--yes",
"github:cressie176/mcp-server",
"--repository-type",
"filesystem",
"--path",
"/path/to/your/data"
]
}
}
}Development
Debugging with MCP Inspector
Use the MCP Inspector to debug and test your server:
npx @modelcontextprotocol/inspector node index.js --repository-type filesystem --path ./test/dataThis will open a web interface where you can:
Test resource and prompt listings
Inspect server responses
Debug communication between client and server
Running Tests
npm testCode Style
npm run lint
npm run formatLicense
ISC
This server cannot be deployed
Maintenance
Related MCP Connectors
An MCP server that gives your AI access to the source code and docs of all public github repos
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
MCP server for AI agent profiles and smart notes. 60+ coding prompt packs with expert personas.
A MCP server built for developers enabling Git based project management with project and personal…
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that enables clients to extract LLM-friendly prompts from documentation in GitHub repositories or hosted websites.2Apache 2.0
- AlicenseNot gradedqualityDmaintenanceAn MCP server that analyzes codebases and generates contextual prompts, making it easier for AI assistants to understand and work with code repositories.18MIT
- FlicenseAqualityFmaintenanceAn enhanced MCP server that fetches prompts from GitHub repositories with intelligent discovery, composition, and management features.713-
- FlicenseAqualityDmaintenanceAn enhanced MCP server that fetches prompts from GitHub repositories with intelligent discovery, composition, and management features.71-