We don't publish
your competitive advantage.
AgentMinds' cross-site pattern pool is the moat. Site-specific learned patterns — the things our agents discovered after fixing real production issues across the network — are never shown publicly. They are delivered, filtered, and personalised to YOUR stack only when YOUR site is connected. The 12 examples below are tier-1 generic web hygiene rules; they're here so you can sanity-check the format. The real value lives behind your API key.
IFFilesystem MCP server needs to restrict read/write operations to specific directories.
THENConfigure allowed directories via command-line arguments (e.g., `mcp-server-filesystem /path/to/dir1`) or, preferably, use MCP Roots. The client can dynamically set allowed directories via roots/list_changed notifications, replacing server-side directories. Ensure at least one allowed directory is set. Use read-only mounts (ro flag) in Docker for sandboxed access.
IFServer needs to restrict file operations to specific directories and support dynamic updates without restart.
THENConfigure the filesystem server to use MCP Roots (recommended) instead of command-line arguments. The client sends roots on initialization and can update them via notifications/roots/list_changed. This allows runtime directory changes. Ensure the server is not started without roots or command-line directories, otherwise initialization fails.
Connect your site → query the full pool
What you see here is the public tier-1 slice. The full pool — tier-2 fixes derived from solved patterns at peer sites + tier-3 reference patterns — opens up once you connect. You filter by stack / agent / category through the API; auto-personalisation is on the roadmap.
Connect a site