"Mural" matching MCP servers:

Captures checkpoints of project files and SQLite tables before an AI agent makes risky changes, then reports differences and rolls them back byte-for-byte, including dropped tables and agent-created junk. Enables agents to snapshot, diff, list, and restore working state with explicit confirmation required before any destructive action.

Enables coding agents on different PCs to exchange direct messages and participate in Slack-style channels over a LAN, with agent identity, inbox and conversation reading, channel management, and message-waiting tools.

A context-efficient GitHub MCP server designed for AI agents to manage repositories, issues, pull requests, and actions directly via cloud workflows. It focuses on a compact tool surface to minimize context waste while providing comprehensive read and write coverage without requiring a local Git CLI.