Exposes a context_folding MCP tool that lets an agent mark conversation history entries (user messages, model replies, tool results) as foldable, keep, or unmarked and replace marked content in outgoing model requests with a head, a concise summary, and an original-entry ID, without altering the client's own full history. Enables listing, paginated reading of originals, layered expansion via previous IDs down to the original, status inspection, and cleanup, with folding applied only when token thresholds and trusted cost-accounting gates are satisfied.
Exposes Claude Code's file editing, command execution, and test running capabilities as composable MCP tools for any MCP-compatible host, enabling code operations via a stateless bridge.
Enables any Model Context Protocol-compatible host (Claude Desktop, Cherry Studio, Cline, MCP Inspector) to call 8 plug-and-play tools over stdio: hotspot ranking, TC3 signing, text chunking, date calculation, read-only SQLite queries, webpage text extraction, JWT decode/verify, and health checks.
Enables LLM clients to invoke standardized MCP tools across stdio, HTTP, and Cloudflare Workers, returning Markdown and structured results; the current scaffold includes an echo tool, with GPT Image generation and editing tools planned.