AiDD (Dev Workflows) MCP server

Integrates file system, code analysis, Git, and execution capabilities to enable AI-driven development workflows across multiple programming languages.
Back to servers
Setup instructions
Provider
Skydeck AI
Release date
Jan 08, 2025
Language
Python
Package
Stats
11.3K downloads
70 stars

SkyDeckAI Code is an MCP (Model Context Protocol) server providing a comprehensive toolkit for AI-driven development workflows. It enables AI assistants to interact with your local environment, performing file operations, code analysis, execution, web searches, and more, creating a powerful development experience where AI can directly assist with software tasks.

Installation

You can install SkyDeckAI Code using the uvx package manager:

# Using uvx
uvx skydeckai-code

Setup with Claude Desktop

To integrate with Claude Desktop, add the following to your claude_desktop_config.json:

{
    "mcpServers": {
        "skydeckai-code": {
            "command": "uvx",
            "args": ["skydeckai-code"]
        }
    }
}

Setup with MseeP AI Helper App

If you're using the MseeP AI Helper app, simply search for "SkyDeckAI Code" in the app and install it.

Key Features

  • File system operations (read, write, edit, move, copy, delete)
  • Directory management and traversal
  • Multi-language code analysis using tree-sitter
  • Code content searching with regex pattern matching
  • Multi-language code execution with safety measures
  • Web content fetching with HTML-to-markdown conversion
  • Multi-engine web search capabilities
  • Batch operations for tool execution
  • Security controls with configurable workspace boundaries
  • Screenshot and screen context tools
  • Image handling tools

Using File System Tools

Basic File Operations

// Reading file content
{
    "files": [{"path": "src/main.py"}]
}

// Writing to a file
{
    "path": "README.md",
    "content": "# My Project\n\nThis is a sample project."
}

// Moving or renaming a file
{
    "source": "old_name.txt",
    "destination": "new_name.txt"
}

// Copying files
{
    "source": "src/utils.py",
    "destination": "src/utils_backup.py"
}

// Deleting files
{
    "path": "temp_file.txt"
}

Advanced File Editing

The edit_file tool allows for pattern-based file editing:

{
    "path": "src/main.py",
    "edits": [
        {
            "oldText": "def old_function():",
            "newText": "def new_function():"
        }
    ],
    "dryRun": false,
    "options": {
        "partialMatch": true
    }
}

Directory Management

// List directory contents
{
    "path": "src"
}

// Create a new directory
{
    "path": "new_folder"
}

// Generate directory tree
{
    "path": ".",
    "include_hidden": false
}

Code Analysis and Search

Analyzing Codebase Structure

The codebase_mapper tool provides comprehensive code structure analysis:

{
    "path": "src"
}

This returns information about classes, methods, functions, and code organization.

Searching Code Content

Use the search_code tool to find patterns in your code:

{
    "patterns": ["function\\s+\\w+", "class\\s+\\w+"],
    "include": "*.js",
    "exclude": "node_modules/**",
    "max_results": 50,
    "case_sensitive": false,
    "path": "src"
}

Code Execution

Running Code in Various Languages

{
    "language": "python",
    "code": "print('Hello, World!')",
    "timeout": 5
}

Supported languages include Python, JavaScript (Node.js), Ruby, PHP, Go, and Rust.

Executing Shell Scripts

{
    "script": "echo \"Current directory:\" && pwd",
    "timeout": 300
}

⚠️ Security Warning: Always review code before execution and understand its purpose.

Web Tools

Fetching Web Content

{
    "url": "https://api.github.com/users/octocat",
    "headers": {
        "Accept": "application/json"
    },
    "timeout": 15,
    "save_to_file": "downloads/octocat.json",
    "convert_html_to_markdown": true
}

Performing Web Searches

{
    "query": "latest python release features",
    "num_results": 8,
    "convert_html_to_markdown": true,
    "search_engine": "bing"
}

Screen Context and Image Tools

Capturing Screenshots

{
    "output_path": "screenshots/capture.png",
    "capture_mode": {
        "type": "named_window",
        "window_name": "Visual Studio Code"
    }
}

Getting System Context

// List active applications
{
    "with_details": true
}

// List open windows
{}

Utility Tools

Batch Operations

Execute multiple operations at once:

{
    "description": "Setup new project",
    "sequential": true,
    "invocations": [
        {
            "tool": "create_directory",
            "arguments": {
                "path": "src"
            }
        },
        {
            "tool": "write_file",
            "arguments": {
                "path": "README.md",
                "content": "# New Project\n\nThis is a new project."
            }
        }
    ]
}

Configuration

You can configure SkyDeckAI Code by creating or editing ~/.skydeckai_code/config.json:

{
    "allowed_directory": "/path/to/workspace"
}

This sets the root directory that the server can access for operations.

Debugging

For debugging, use the MCP Inspector:

npx @modelcontextprotocol/inspector run

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "skydeckai-code" '{"command":"uvx","args":["skydeckai-code"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "skydeckai-code": {
            "command": "uvx",
            "args": [
                "skydeckai-code"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "skydeckai-code": {
            "command": "uvx",
            "args": [
                "skydeckai-code"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later