# KuvopLLC/better-bear [Health: Active]

**Category:** 🏢 Workplace & Productivity  
**Repository:** https://github.com/KuvopLLC/better-bear/tree/main/mcp-server  
**GitHub Stars:** 68  
**npm Downloads (last month):** 327  
**Views:** 3  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/kuvopllc-better-bear

## Description
MCP server for Bear notes via CloudKit — CRUD, tags, TODOs, attachments, search, front matter, stats, and health checks. Install via npx better-bear.

## Tools
Capabilities this server exposes over MCP:

- **bear_list_notes** — List Bear notes with optional tag filtering. Returns an array of notes with IDs, titles, tags, pin status, and modification dates. Each note includes two tag fields: 'tags' mirrors Bear's CloudKit index verbatim (includes ancestor expansions — a note tagged #parent/child will show both 'parent' and 'parent/child'); 'attached_tags' shows only leaf tags (the most-specific tag on each branch). Notes with 'locked: true' are private/encrypted in Bear and their body content is not searchable — if a search returns no results, check whether the relevant note is locked. Use bear_get_note to read the full content of a specific note.
- **bear_get_note** — Get a single Bear note's full content and metadata by ID. Returns the note title, tags, full markdown text, and dates. The response includes 'tags' (CloudKit index, may contain ancestor tags like 'parent' for a note tagged '#parent/child') and 'attached_tags' (leaves only). If the note is locked/private, 'locked: true' will be included in the response. Use the 'raw' option to get just the markdown without metadata.
- **bear_search** — Full-text search across Bear note titles, tags, and body content. Returns matching notes ranked by relevance (title matches first, then tag, then body). Body matches include a text snippet with surrounding context. Locked/private notes will match by title but may not match body searches — results include 'locked: true' for these notes. If you can't find content you expect, try listing notes to check if the relevant note is locked.
- **bear_get_tags** — Get the full tag hierarchy from Bear. Returns all tags with their note counts and pin status. Useful for understanding how notes are organized.
- **bear_create_note** — Create a new Bear note with a title, optional body text, tags, and YAML front matter. Hashtags written inline in the body (e.g. '#my_tag' or '#parent/child') are extracted and registered as real tags on the note, matching Bear's desktop-app behaviour. Tags from the 'tags' array are indexed regardless of whether they appear in the body. Hierarchical tags like '#parent/child' also index every ancestor (so they show up under #parent in Bear's sidebar). Front matter is stored as a collapsed metadata block at the top of the note. Returns the new note's ID.
- **bear_edit_note** — Edit an existing Bear note. Provide 'append_text' to add text, 'body' to replace content, or 'set_frontmatter'/'remove_frontmatter' to edit YAML front matter fields. Front matter edits can be combined with each other but not with body/append.
- **bear_trash_note** — Move a Bear note to the trash. This is a soft delete — the note can be recovered from Bear's trash. The note is identified by its ID.
- **bear_sync** — Trigger a sync of Bear notes from iCloud. Normally an incremental sync fetching only changes. Use 'full' to force a complete re-sync. Most read operations auto-sync when the cache is stale, so manual sync is rarely needed.
- **bear_list_todos** — List Bear notes that have incomplete TODO items (markdown checkboxes like '- [ ]'). Returns each note's title, tags, and counts of complete/incomplete items.
- **bear_get_todos** — Get all TODO items from a specific Bear note. Returns each item's text, completion status, and index number (use the index with bear_toggle_todo to toggle items).
- **bear_toggle_todo** — Toggle a specific TODO item in a Bear note between complete and incomplete. The item_index is 1-based — use bear_get_todos first to see the list with index numbers.
- **bear_attach_file** — Attach a file or image to an existing Bear note. The file is uploaded to iCloud and embedded in the note's markdown. Supports common image formats (jpg, png, gif, webp, heic) and other file types (pdf, zip, etc.). By default the attachment is appended to the end. Use 'after' or 'before' to place it relative to text in the note, or 'prepend' to put it right after the title.
- **bear_archive_note** — Archive a Bear note. Archived notes are hidden from the main list but not deleted. Use 'undo' to unarchive.
- **bear_add_tag** — Add a tag to an existing Bear note. The tag is inserted into the note's markdown. Hierarchical tags like 'parent/child' also index every ancestor — so the note becomes discoverable under both #parent and #parent/child in Bear's sidebar.
- **bear_remove_tag** — Remove a tag from a specific Bear note. Works on any tag visible in 'tags' on the note — including ancestor tags like 'parent' that exist only as hierarchical expansions. Removing a hierarchical leaf like 'parent/child' also drops orphaned ancestors from the tag index.
- **bear_rename_tag** — Rename a tag across all Bear notes. Every note containing the old tag will be updated.
- **bear_delete_tag** — Delete a tag from all Bear notes. The tag text is removed but notes are preserved.
- **bear_find_untagged** — List Bear notes that have no tags assigned.
- **bear_note_stats** — Get statistics about the Bear notes library: total notes, words, tags, pinned, archived, trashed, notes with TODOs, oldest/newest dates, and top 10 tags by note count.
- **bear_find_duplicates** — Find notes with duplicate titles. Returns groups of notes sharing the same title with their IDs and modification dates. Useful for cleaning up after imports or sync conflicts.
- **bear_health_check** — Run a health check on the Bear notes library. Reports duplicate titles, empty notes, notes stuck in trash, sync conflicts, orphaned tags, untagged notes, and oversized notes. Use this to identify cleanup opportunities or diagnose sync issues.
- **bear_context_setup** — Initialize a context library — a curated, synced folder of Bear notes optimized for LLM consumption. Creates the directory structure and config. After setup, tag Bear notes with #context (or a custom prefix) and use bear_context_sync to pull them in. One-time operation.
- **bear_context_sync** — Sync qualifying Bear notes to the local context library. Adds new notes, updates changed notes, and removes notes that no longer qualify (tag removed, trashed, etc.). Regenerates the index. Only touches the bear/ directory — external/ and inbox/ are untouched. Call this when the user asks to sync, refresh, or update their context.
- **bear_context_index** — Get the context library index — a structured table of contents of all files (Bear notes, external files, inbox). Read this FIRST before answering questions from context. Use it to identify which files to fetch, rather than loading everything. Includes cache freshness metadata.
- **bear_context_fetch** — Load the full content of specific files from the context library. Pass relative paths like 'bear/arch-overview.md' or 'external/jira-ticket.md'. Use after reading the index to load only relevant files — never load everything.
- **bear_context_search** — Full-text search across the entire context library (Bear notes + external files + inbox). Returns matching snippets with filenames and origin labels. Use when the index alone isn't enough to find the right file.
- **bear_context_add** — Add a Bear note to the context library by tagging it with #context. Optionally specify a subtag for grouping (e.g., subtag 'jira' → #context/jira). Triggers a sync after tagging.
- **bear_context_remove** — Remove a Bear note from the context library by removing its #context tag. Triggers a sync to delete the local file.
- **bear_context_status** — Get context library health and stats: Bear note count, external file count, inbox count, total tokens, last sync time, group breakdown, and warnings (stale cache, expired externals, oversized files, untriaged inbox items).
- **bear_context_import** — Import external content into the context library. Content is written to the external/ directory with YAML front matter (source, group, summary, date). Use this to add non-Bear content like Jira tickets, Slack threads, API docs, or any markdown. The content is passed via stdin and a filename must be provided.
- **bear_context_ingest** — Scan the inbox/ directory and list all untriaged files. Returns filename, size, content preview (first 500 chars), and any detected YAML front matter for each file. Does NOT modify anything — use bear_context_triage to act on files.
- **bear_context_triage** — Triage a file in the inbox. Three actions: 'keep' moves it to external/ with optional group/summary metadata. 'push_to_bear' creates a Bear note tagged #context (+ optional subtag) and deletes the inbox file. 'discard' deletes the file. All actions regenerate the index.
- **bear_context_push_to_bear** — Push an external file to Bear as a new note. Creates a Bear note from the file content, tags it with #context (+ optional subtag), and removes the original external file. Use when external content has matured enough to become a permanent Bear note.
- **bear_context_set_prefix** — Change the context library's tag prefix and re-tag every Bear note that currently uses the old prefix. Sub-tags are preserved — `#context/research` becomes `#<new>/research`. Updates both the markdown body and the CloudKit tag index, and persists the new prefix to the context config. Useful when aligning the qualifier tag with a broader naming scheme like Johnny Decimal (e.g. '10-projects'). Run `bear_context_sync` afterwards to refresh the library.
- **bear_context_remove_external** — Remove a file from the external/ directory in the context library. Deletes the file and regenerates the index. Use when external content is no longer needed.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "better-bear": {
    "command": "npx",
    "args": ["-y","better-bear"]
  }
}
```

## Documentation

## What KuvopLLC/better-bear does

KuvopLLC/better-bear connects MCP clients to Bear notes through Apple CloudKit. It lets an agent read, search, create, edit, archive, trash, tag, and inspect notes, while also handling TODO items and file attachments. Library-level operations include tag discovery, untagged-note detection, duplicate-title searches, statistics, and health diagnostics.

The server also provides a context library for turning selected Bear notes into a local, curated knowledge base. Notes marked for the library can be synchronized as markdown files, accompanied by a manifest and freshness information. Agents can then inspect the index, fetch selected files, or search the context files directly without a vector database or separate RAG pipeline.

## How it works

MCP communication uses standard input and output. For each operation, the server starts a corresponding `bcli` command. `bcli` is a native macOS binary that communicates with Bear's CloudKit container, so the integration does not depend on Bear's URL scheme or AppleScript.

Authentication is handled through iCloud using `bcli auth`. Credentials are kept locally in `~/.config/bear-cli/auth.json` and refreshed when they expire. Notes remain synchronized through CloudKit across devices. The server and its local caches do not send personal data to an external service; network access goes to Apple CloudKit for notes, GitHub for updates, and npm for package resolution.

## Setup and configuration

The standard setup requires Node.js 18 or newer, the `bcli` binary, and iCloud authentication. The installation script installs `bcli`, runs the setup needed for authentication, and configures the MCP server for Claude Desktop and Claude Code.

A direct package-based configuration can run the server with:

```sh
claude mcp add better-bear -- npx -y better-bear
```

The `bcli mcp install` command supports Desktop-only and Code-only installations, JSON configuration output, and setup through a released `.mcpb` bundle. Authenticate before using note tools so the server can access the Bear CloudKit container.

## Tools and capabilities

Core note and library tools include:

- Synchronize notes incrementally or with a full sync.
- List, retrieve, create, edit, archive, trash, and search notes.
- Search by text with `since` and `before` date filters.
- Add, remove, rename, and delete tags, plus list tag counts.
- Find untagged notes and notes with duplicate titles.
- Attach images or other files to notes.
- List incomplete TODOs, inspect a note's TODO items, and toggle completion.
- Report note counts, word totals, top tags, and library health.

Context-library tools initialize the library, synchronize qualifying notes, expose its index and freshness data, fetch files by path, search all context files, add or remove notes, and report token counts, warnings, and status.

## Limitations and notes

The integration depends on Bear, iCloud authentication, CloudKit access, Node.js 18 or newer, and the macOS `bcli` binary. It communicates with MCP clients over stdio and stores authentication data and note caches locally. The context library is based on curated markdown files and an index manifest rather than a vector database.

_Full upstream README: https://allmcps.com/mcp/kuvopllc-better-bear/readme_