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.
IFI need to find MCP servers, CLI tools, or AI coding site_1 relevant to a specific keyword or task.
THENUse the search_agents tool via your MCP client. Provide a keyword query (e.g., 'browser automation'). The tool returns a list of matching site_1 from the A2ASearch directory. Example prompt: 'Search for MCP servers that can help me work with databases'.
IFWhen you need to find MCP servers, AI site_1, CLI tools, or agent skills for your workflow.
THENInstall the A2ASearch MCP server into your MCP client (Claude, Cursor, Windsurf, Cline, etc.) using the command 'npx -y a2asearch-mcp' and use its built-in tools (search_agents, get_agent, list_agents) to query the indexed directory. No authentication or API key required.
IFNeed to find an MCP server, AI coding agent, CLI tool, or agent skill for a specific task or integration.
THENInstall the a2asearch-mcp MCP server (via npx a2asearch-mcp) in your MCP client (Claude, Cursor, etc.). Use the `search_agents` tool with a keyword query to find relevant tools. Alternatively, use the CLI directly with `a2asearch --type <type> <query>` or the REST API at `https://a2asearch.ai/api/v1/site_1?q=<query>`. No authentication required.
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