All memos tagged #model-context-protocol

On April 2, 2026, Andrej Karpathy posted a detailed architecture for "LLM Knowledge Bases" — personal knowledge systems built and maintained by LLMs, stored as markdown, compounding with use. He...

MythOS works on Claude mobile — iOS and Android — via OAuth. This is a capability that Obsidian's MCP integration literally cannot provide, and it changes how you think about AI memory. What This...

The Session Memory Protocol gives your AI collaborator persistent memory across conversations using MythOS daily memos. No CLAUDE.md hacks, no manual file management — just structured, cross-client...

MythOS MCP (Model Context Protocol (MCP)) connects your MythOS knowledge library to AI assistants like Claude, Cursor, Windsurf, and any MCP-compatible client. It lets you search memos, read content,...

Reference for all MythOS MCP server capabilities. Endpoint: https://mythos.one/api/mcp. Auth: OAuth 2.0 (Claude connectors) or x-mythos-key header (Claude Code, npm package). getcontext (read-only,...

The Model Context Protocol (MCP) is an open protocol developed by Anthropic and donated to the Linux Foundation that standardizes how Artificial Intelligence (AI) models connect to external tools,...

Implicit loading is a design pattern in MythOS MCP where a collaborator's preferences, style rules, and identity context are automatically included in MCP tool responses — without requiring a...

Beehiiv MCP is a model-context-protocol integration that connects the Beehiiv newsletter platform directly to AI assistants like Claude, ChatGPT, Gemini, and Perplexity. Announced in March 2026, it...

Watch Contexts model-context-protocol