Enables AI coding assistants to perform multi-engine web searches, site-specific searches, and structured webpage content extraction via MCP stdio, without requiring any API keys.
Enables MCP chat clients to read explicitly shared local source files and search results without spending local model quota, while also providing an experimental quota-relay workflow for extended modes.
This MCP server enables asynchronous, event-driven orchestration of long-running AI coding agents, allowing a leader session to dispatch jobs that execute in the background, survive disconnects, and provide queryable status and resumability without blocking model turns.