F
licenseB
qualityF
maintenanceProvides sophisticated context management for Claude, enabling persistent context across sessions, project-specific organization, and conversation continuity.
4
15
-
Context Keeper
Click on "Deploy 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., "@Context Keeperwhat was I just working on?"
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.
Context Keeper
An MCP server that gives Alexa+ persistent context memory across interactions.
Problem
Alexa+ is stateless by default. Ask a question, get an answer, and five minutes later that context is gone. You have to repeat yourself. This is a real friction point when using voice while cooking, working, or driving.
Related MCP server: Personal Context Technology MCP Server
Solution
Context Keeper is a self-hosted MCP server built with FastMCP (Python) that maintains a lightweight per-user context thread across separate Alexa+ interactions. It uses the Streamable HTTP transport, spec 2025-11-25+.
Tools Exposed
start_context(user_id, topic)— begins a new context threadquery_context(user_id)— retrieves the current context threadlist_contexts()— lists all active context threads
How It Works
The server registers three MCP tools via the @mcp.tool() decorator.
When an Alexa+ agent calls query_context, it receives the user's
current topic and history, then answers with continuity folded in.
Run It
uv add fastmcp
uv run server.pyThis server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues
Related MCP Connectors
Cross-LLM persistent memory: store context once, recall it from any AI model.
Persistent context for Claude. Your AI always knows your projects and next actions across sessions.
Memory for deep conversational context across any platform
Shared, versioned context that humans and AI agents can publish, review, annotate, and continue.
Related MCP Servers
- AlicenseDqualityDmaintenanceEnables AI assistants to access and update personalized context data, creating persistent memory between sessions.14MIT
- AlicenseNot gradedqualityDmaintenanceEnables MCP-compatible AI clients to store and recall voice conversation context by caching user and AI utterances, supporting formatted context summaries for multi-turn voice interactions.MIT
- AlicenseNot gradedqualityCmaintenanceEnables voice-first shared object memory for Alexa+, letting users record where items were last reported, retrieve authorized locations, correct stale records, check shared items in and out, run guided Lost Mode searches, and manage privacy-aware access.MIT