mcp-server-osascript
Secure AppleScript execution for AI applications via Model Context Protocol with configurable security profiles and automatic TCC permission handling.
README
MCP osascript Server
Secure AppleScript execution for AI applications via Model Context Protocol with configurable security profiles and automatic TCC permission handling.
Overview
This MCP server provides a bridge between AI models and macOS automation through secure AppleScript execution. It features a modular architecture with configurable security profiles, automatic permission management, and comprehensive error handling.
Installation
Development Setup
# Clone and setup dependencies
uv sync
# Optional: Development mode installation
uv pip install -e .
Production Installation
# System-wide installation with uvx
uvx install /path/to/mcp-server-osascript
# From Git repository
uvx install git+https://github.com/your-username/mcp-server-osascript.git
# From PyPI (when published)
uvx install mcp-server-osascript
Usage
Production Usage
# After uvx installation (available system-wide)
mcp-server-osascript
Development Usage
# From project directory
uv run mcp-server-osascript
# From any directory
uv run --project /path/to/mcp-server-osascript mcp-server-osascript
# Alternative: Direct module execution
uv run python -m mcp_server_osascript.server
MCP Client Configuration
Add this configuration to your MCP client:
Production Configuration:
{
"mcpServers": {
"osascript": {
"command": "mcp-server-osascript",
"args": []
}
}
}
Development Configuration:
{
"mcpServers": {
"osascript": {
"command": "uv",
"args": ["run", "--project", "/path/to/mcp-server-osascript", "mcp-server-osascript"]
}
}
}
Architecture
The server is built with a modular architecture consisting of six focused components:
- Security System: Configurable risk assessment with three security profiles
- Execution Engine: Direct osascript execution with timeout management
- Permission Handler: Automatic TCC permission dialog triggering
- Response Builder: Standardized API response formatting
- User Interface: Interactive confirmation dialogs
- Server Core: FastMCP integration and tool registration
Features
Configurable Security Profiles
- Strict: Maximum security with blocked dangerous operations
- Balanced: Recommended default with risk warnings (default)
- Permissive: Minimal restrictions with audit logging
Advanced Permission Management
- Automatic TCC permission dialog triggering
- Intelligent error parsing and user guidance
- Support for common macOS applications
- Manual permission configuration instructions
Comprehensive Tool Interface
- Single unified
execute_osascripttool - Dry-run mode for script analysis without execution
- Configurable execution timeouts
- Detailed success and error reporting
Tool Reference
execute_osascript
Execute or analyze AppleScript/JavaScript code with comprehensive security and permission handling.
Parameters:
script(str): AppleScript or JavaScript code to executeexecution_timeout(int): Timeout in seconds (default: 30)security_profile(str): Security level - "strict", "balanced", or "permissive" (default: "balanced")enable_auto_permissions(bool): Auto-trigger TCC permission dialogs (default: true)dry_run(bool): Analyze script without executing (default: false)
Response Structure:
{
"status": "success|error",
"timestamp": "2024-01-01T12:00:00.000Z",
"data": {
"stdout": "execution output",
"stderr": "error output",
"execution_time": 1.23
}
}
Error Response:
{
"status": "error",
"timestamp": "2024-01-01T12:00:00.000Z",
"error": {
"type": "SECURITY_BLOCKED|TCC_PERMISSION_DENIED|EXECUTION_TIMEOUT|SYNTAX_ERROR",
"message": "Human-readable error description",
"details": "Additional error context and repair suggestions"
}
}
Security Features
Script Analysis
- Pattern matching for dangerous operations
- Risk scoring and classification
- High-risk operation confirmation prompts
- Comprehensive audit logging
Permission Management
- TCC error code detection (-1743)
- Application-specific permission guidance
- Automatic permission dialog triggering
- Manual configuration instructions
Execution Safety
- Direct execution for proper TCC dialog display
- Configurable timeout protection
- Subprocess error handling
- Memory and resource management
System Requirements
- Operating System: macOS (required for AppleScript runtime)
- Python: 3.10 or higher
- Package Manager: uv (recommended) or pip
- Permissions: User must grant necessary TCC permissions for target applications
Development
Testing
# Validate syntax for all modules
python3 -m py_compile mcp_server_osascript/*.py
# Test individual modules
python3 -c "from mcp_server_osascript.security import SecurityProfileManager; print('Security module OK')"
Architecture Overview
The codebase follows a modular design with clear separation of concerns:
- Security assessment and policy enforcement
- Script execution and subprocess management
- Permission handling and TCC error parsing
- Standardized response formatting
- User interface and confirmation dialogs
License
MIT License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.