Enables AI agents to perform read-only static analysis of Node.js backend projects, detecting database query anti-patterns, async bottlenecks, connection pooling mistakes, and dependency hygiene issues while returning structured evidence-backed findings.

Enables a language model to perceive a robot's surroundings, navigate to referenced objects, count instances, and stop when finished, via tools for viewing, grounding, driving, and counting.

A command-line interface for interacting with MCP (Model Context Protocol) servers using both stdio and HTTP transport.

Draw your app's architecture on a live canvas and flag the bottlenecks and security gaps.