pulsemcp verified Safe content atomic mcp-remote

Scenic GUI Automation

This MCP server provides AI-driven automation and testing capabilities for Scenic Elixir GUI applications through a dual-architecture implementation combining an Elixir TCP server with a TypeScript MCP interface. Built using Elixir with the Scenic framework and TypeScript with the MCP SDK, it enables keyboard input simulation with support for special keys (enter, escape, arrow keys, function keys) and modifier combinations, mouse interaction including cursor movement and clicking with configurable button support, real-time connection status monitoring, and automatic Scenic viewport discovery across different application architectures. The implementation features a TCP server running on port 9999 that integrates directly with Scenic's ViewPort.Input system for reliable event injection, comprehensive error handling with retry logic, and a clean separation between the Elixir backend and TypeScript MCP frontend, making it valuable for automated testing of Scenic applications, AI-assisted GUI interaction workflows, and development scenarios requiring programmatic control of Elixir-based user interfaces.

Cognium trust score

94%

Tier

Verified

Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.

Scan details: Circle-IR · 2026-09-28 · Appeal

View full trust & usage report →

Metadata

Version: 1.0.0
Skill type: atomic
Execution layer: mcp-remote
Category: monitoring
Source: PulseMCP
Repository: github.com/scenic-contrib/scenic_mcp_experimental
Author type: human
Last scanned: 2026-09-28
Updated: 2026-09-28

View source Find related skills

MCP

Resolve Scenic GUI Automation from your agent

Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.

One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.

claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp

Swap --scope user for --scope project to commit it to .mcp.json.

Your client Same endpoint everywhere; only the config key differs. The full list is in the descriptor.

Claude Desktop · Settings → Connectors → Add custom connector

https://api.skillsregistry.net/mcp

Paste the URL as the connector endpoint. No authentication.

ChatGPT · Settings → Connectors → Create (developer mode) → MCP server URL

https://api.skillsregistry.net/mcp

Authentication: none. Works in chat and deep research — the server exposes the connector search and fetch tools.

Codex CLI · ~/.codex/config.toml

[mcp_servers.skillsregistry]
url = "https://api.skillsregistry.net/mcp"