Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@CONTINUITY save session with handoff for my-project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Session state persistence for MCP systems: crash recovery, a decision registry, and context compression for long-running AI sessions.
A long working session with an AI assistant accumulates real state — decisions made, approaches tried and rejected, context that took real back-and-forth to establish. A crash, a context-window limit, or just closing the window loses all of it, and re-establishing that state by hand is expensive.
Related MCP server: JauMemory MCP Server
CONTINUITY checkpoints session state as it develops, logs decisions explicitly rather than letting them live only in conversation history, and compresses context so a session can be resumed without replaying the entire prior conversation to get back to where it left off.
CONTINUITY is the session-recovery layer in a larger cognitive-infrastructure stack. See davidkirsch.me/builds for the rest.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Long-term memory for AI assistants. Hybrid retrieval, query expansion, auto-topics.
Persistent memory for AI agents. Search, store, and recall across sessions.
Persistent memory and drift detection for AI agents across session restarts.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/duke-of-beans/CONTINUITY'
If you have feedback or need assistance with the MCP directory API, please join our Discord server