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.
IFMCP tool fails with 'Not connected' error on Windows when using npx directly as command.
THENSet the MCP server command to 'cmd' and add args ['/c', 'npx', '-y', 'package-name']. Install the package globally using 'npm install -g @modelcontextprotocol/server-<name>' to avoid temporary execution path issues on Windows.
IFClaude Desktop logs 'Unexpected end of JSON input' error when connecting to an MCP server.
THENEnsure the MCP server configuration uses the correct 'command' and 'args' fields for STDIO transport. Do not set 'command' to 'echo' or include a 'server' object with TCP parameters unless the server explicitly supports SSE/TCP. For the postgres MCP server, use a command like 'npx -y @modelcontextprotocol/server-postgres' and pass connection details via environment variables or command-line arguments. Verify that the server process outputs valid JSON-RPC messages on stdout.
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