SkyDeckAI Code

Provides a comprehensive set of AI-driven development tools for local and remote resources.

python

77

GitHub Stars

python

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

Available tools

get_allowed_directory

Get the current allowed directory path

update_allowed_directory

Change the allowed directory to a new path

create_directory

Create a new directory, including nested paths

write_file

Create or overwrite a file with new content

edit_file

Edit a text file by applying specified edits with optional dry-run preview

read_file

Read contents of one or more specified files

list_directory

List files and subdirectories within a directory

move_file

Move or rename a file or directory to a new location

copy_file

Copy a file or directory to a new location, with optional recursive behavior

search_files

Search for files by name pattern across the workspace

delete_file

Delete a file or empty directory

get_file_info

Retrieve metadata for a file (size, timestamps, permissions)

directory_tree

Generate a recursive tree view of a directory structure

read_image_file

Read an image file and return its contents as base64 data

codebase_mapper

Analyze code structure across files and extract classes, functions, modules, and relationships

search_code

Search for text patterns in code using regular expressions with optional file filters

execute_code

Execute code in supported languages with safety checks and timeouts

execute_shell_script

Run shell scripts with safety controls within the allowed directory

web_fetch

Fetch content from a URL with optional HTML-to-Markdown conversion and optional file saving

web_search

Perform a multi-engine web search and return concise results

capture_screenshot

Capture screenshots of the screen or a specific window

get_active_apps

List currently active applications and optional details about windows

get_available_windows

Provide detailed information about open windows on the screen

get_system_info

Return comprehensive details about the host system

batch_tools

Execute multiple tool invocations in a single request, with optional sequential or parallel execution

think

Document reasoning without making changes to the workspace

todo_read

Read the current workspace todo list

todo_write

Replace the entire todo list for sequential execution workflow

todo_update

Update a specific todo item by ID with new values