An MCP server and CLI for Bear notes that syncs with CloudKit, letting clients list, search, create, edit, tag, and attach files to notes. It also supports a curated "context library" that syncs selected Bear notes into an index-first folder structure for LLM use.
From the registry: MCP server for Bear notes — read, search, create, edit, tag, and manage notes via CloudKit
$ curl -sL https://raw.githubusercontent.com/KuvopLLC/better-bear/main/install.sh | bashhttps://github.com/KuvopLLC/better-bear/blob/main/install.sh},{Please install the `better-bear` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install better-bear CLI** — Install the `bcli` binary using the project's install script. Run: `curl -sL https://raw.githubusercontent.com/KuvopLLC/better-bear/main/install.sh | bash` (https://github.com/KuvopLLC/better-bear/blob/main/install.sh},{)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","better-bear"]
Note: README provides a direct MCP command for Claude Code: `claude mcp add better-bear -- npx -y better-bear`, which yields the canonical stdio shape `command: npx`, `args: [-y, better-bear]`. Authentication with iCloud is handled separately via `bcli auth` as a prerequisite, not via MCP config env vars. No env vars are documented in the provided README.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.