"Dart" matching MCP servers:

An MCP server that provides persistent memory for AI agents, enabling context retention across sessions and supporting vibe-loop workflows where agent promises and deliverables are tracked and validated.

Enables agents to monitor token/usage limits and persist work checkpoints, allowing them to pause, resume, and track progress across sessions.

Presents multiple stdio backend tool servers to an MCP client as one aggregated server, sharing those backend processes across concurrent agent sessions through a background broker while namespacing and routing each tool call to the right backend. Servers can be run shared, per-session, or lazily, with automatic restart and request ID remapping so many sessions coexist without collisions.

Enables a stateless MCP server on Cloudflare Workers, providing a simple greeting tool for testing and integration.

Enables running a stateless MCP server on Cloudflare Workers via the Agents SDK's createMcpHandler, registering simple tools such as a greeting tool with no Durable Objects or persistent state.