Touchpoint-Labs/touchpoint

Overview

A cross-platform accessibility API paired with a Model Context Protocol (MCP) server. It enables AI agents to read and interact with desktop graphical user interfaces programmatically. Written in Python, it exposes the underlying accessibility tree to assist automation and agent-driven workflows.

Best for

Best for
Developers building AI agents that need to observe and control desktop applications programmatically

Use cases

• Automating GUI tasks with natural language commands via an AI agent
• Building accessibility test suites for desktop applications
• Integrating headless desktop interaction into custom agent pipelines

Notes

A cross-platform accessibility API paired with a Model Context Protocol (MCP) server. It enables AI agents to read and interact with desktop graphical user interfaces programmatically. Written in Python, it exposes the underlying accessibility tree to assist automation and agent-driven workflows.

37 stars on GitHub. Last updated 2026-04-25. Licensed MIT.

Use cases

• Automating GUI tasks with natural language commands via an AI agent
• Building accessibility test suites for desktop applications
• Integrating headless desktop interaction into custom agent pipelines

Pros

• Cross-platform support (Windows, macOS, Linux) via accessibility APIs
• Simple MCP server interface for agent integration
• Open source and written in a widely used language (Python)

Cons

• Small community (37 GitHub stars) — limited support and documentation
• Relies on accessibility APIs, which may miss custom or non-standard UI elements
• Early-stage project — API stability and feature completeness not guaranteed

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.