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.
IFAI agent encounters a task it cannot perform because the required MCP server is not installed.
THENUse forage_search to find the relevant MCP server, then forage_install to add it. The agent gains new tools immediately without restarting the session.
IFWhen an MCP host connects to many servers with hundreds of tools, loading all tool definitions into the model's context window upfront wastes tokens, increases latency, and degrades model performance.
THENImplement progressive tool discovery: defer injection of tool definitions into the model's context. Provide a lightweight search_tools meta-tool for the model to discover tools on demand. Load full definitions only when needed. Implement a threshold (e.g., 1-5% of context window) to switch from upfront loading to progressive discovery. Use a three-layer approach: Catalog (search), Inspect (get details), Execute (call tool). Optionally support dynamic server management by connecting to servers only when needed.
IFMCP server tool with an array-of-objects parameter is not listed in Claude Desktop's available tools, even though other tools work and the tool appears in the MCP Inspector.
THENRefactor the tool parameter to avoid arrays of objects. Use alternative representations such as array of strings (e.g., pairs), stringified JSON (parse server-side), or nested arrays if strings are acceptable. For example, replace an `edits: [{oldText, newText}]` parameter with multiple string parameters (e.g., `oldText`, `newText`) for single edits, or accept a flat array of alternating strings.
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