Cursor Buddy

Provides a context-aware AI partner with access to project rules, knowledge, and task history; supports real-time updates and fast search across your codebase.

GitHub Stars

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "omar-haris-cursor-buddy-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-v",
        "/path/to/your/project/.buddy:/home/buddy/.buddy",
        "-e",
        "BUDDY_PATH=/home/buddy/.buddy",
        "ghcr.io/omar-haris/cursor-buddy-mcp:latest"
      ],
      "env": {
        "BUDDY_PATH": "/home/buddy/.buddy"
      }
    }
  }
}

Cursor Buddy MCP transforms your AI assistant into a context-aware coding partner. It centralizes project guidelines, rules, and history so your AI stays aligned with your codebase as your project evolves, while providing real-time updates and fast, context-rich search.

How to use

You integrate the Cursor Buddy MCP server with an MCP client to give your AI access to your project’s rules, knowledge, and todos. Once connected, your AI can query coding standards, search project documentation, review implementation history, and create or track TODOs. The server monitors your project files and automatically reloads content to keep responses fresh, so you get up-to-date guidance and contextual answers as you work.

How to install

Prerequisites: You need Docker installed on your machine to run the MCP server container.

Pull the latest Cursor Buddy MCP image from the registry.

docker pull ghcr.io/omar-haris/cursor-buddy-mcp:latest

Configure the MCP connection in your project by creating or editing the MCP config file at .cursor/mcp.json using the provided snippet.

{
  "mcpServers": {
    "cursor-buddy-mcp": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-v", "/path/to/your/project/.buddy:/home/buddy/.buddy",
        "-e", "BUDDY_PATH=/home/buddy/.buddy",
        "ghcr.io/omar-haris/cursor-buddy-mcp:latest"
      ]
    }
  }
}

Create the internal data folders for the server within your project. This stores rules, knowledge, todos, database, history, and backups.

mkdir -p .buddy/{rules,knowledge,todos,database,history,backups}

Additional setup notes

This setup uses a drop-in Docker container to integrate Cursor Buddy MCP with your project. The environment variable path inside the container is configured to point to the mounted buddy data directory.

Configuration examples

The following is the exact configuration snippet you would place in your MCP config to run Cursor Buddy MCP in Docker and point it at your project data.

{
  "mcpServers": {
    "cursor-buddy-mcp": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-v", "/path/to/your/project/.buddy:/home/buddy/.buddy",
        "-e", "BUDDY_PATH=/home/buddy/.buddy",
        "ghcr.io/omar-haris/cursor-buddy-mcp:latest"
      ]
    }
  }
}

Available tools

buddy_get_rules

Fetch coding standards and guidelines with filtering by category or priority and support for multiple rule types.

buddy_search_knowledge

Search project documentation with full-text search across all knowledge and filters for category and tags.

buddy_manage_todos

List and update tasks; track progress with feature-based organization and completion status.

buddy_get_database_info

Retrieve database schema information and validate queries with examples.

buddy_history

Track implementation changes and search history to review feature development.

buddy_backup

Create and manage automatic backups of important files before modifications.

Built by

VeilStrat

AI signals for GTM teams