ContextStream is a Model Context Protocol (MCP) server: Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP). In practice that means any MCP-compatible AI assistant can call ContextStream's tools directly — the model decides when to use them in a conversation or agent run.
It's a hosted (remote) server — point your client at https://mcp.contextstream.io/mcp?default_context_mode=fast&src=registry and you're connected, with nothing to install locally. The current release is v0.5.35, published under the MIT license, with source at contextstream/mcp-server on GitHub, where it has earned 40 stars.
ContextStream is listed under Memory on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain ContextStream for contextstream.io, claim this listing to verify ownership, earn the Verified badge, and keep the details current.