# akseyh/bear-mcp-server [Health: Active]

**Category:** 🛠️ Other Tools and Integrations  
**Repository:** https://github.com/akseyh/bear-mcp-server  
**GitHub Stars:** 45  
**Views:** 4  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/akseyh-bear-mcp-server

## Description
Allows the AI to read from your Bear Notes (macOS only)

## Claude Desktop Quick Installation
Heuristic fallback — verify the package name and runner against the repository README before running it. Uses `npx` (confidence: low):

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

## Documentation

## What akseyh/bear-mcp-server MCP server does

akseyh/bear-mcp-server MCP server gives an MCP-compatible client read access to a Bear Notes library. It works with the SQLite database used by Bear and exposes three operations: retrieving notes, searching notes for text, and listing all tags. The server is intended for local Bear data on macOS, not for a hosted or cross-platform notes service.

The available functionality is read-oriented. Based on the listed tools, an agent can inspect existing notes, find notes matching a term or phrase, and discover the tags present in the library. There is no documented tool for creating, editing, deleting, or tagging notes.

## How it works

Bear stores its notes in a SQLite database. When akseyh/bear-mcp-server MCP server starts, it runs SQL queries against that database and makes the results available through MCP tools. The client communicates with the server using the configured local process, while the server reads the database supplied by the Bear installation.

The README identifies these MCP tools:

- `get_notes` retrieves all notes.
- `get_tags` returns all tags.
- `get_notes_like` searches for notes containing specified text.

The database must be accessible to the process running the server. With Docker, this is handled by mounting Bear's macOS application-data directory into the container at `/app/db`.

## Setup and configuration

The project requires Node.js, the Bear application on macOS, and access to Bear's database. The source installation flow is to clone the repository, enter its directory, install npm dependencies, and run the build script. The README also provides an npm client configuration that starts the published `bear-mcp-server` package with `npx`.

A Docker configuration is documented as an alternative. It runs the `akseyh/bear-mcp-server` image and mounts the local Bear database directory. The path shown in the README contains a user-name placeholder, so it must be replaced with the actual macOS user path before use. Docker is useful when the server process should run in a container while still reading the local database through the mounted volume.

Claude Desktop is the explicitly documented client. Its MCP configuration uses a server entry named `bear`; the npm option launches the server with `npx`, while the Docker option launches it with `docker run`.

## Tools and capabilities

akseyh/bear-mcp-server MCP server supports three documented capabilities:

- Retrieve all available Bear notes with `get_notes`.
- Search note contents using `get_notes_like`.
- List the Bear library's tags with `get_tags`.

These tools fit workflows such as finding a stored career note, reviewing a local knowledge base, or identifying tags before narrowing a search. The material does not describe filtering parameters beyond text search, result pagination, note updates, or attachment handling.

## Limitations and notes

The server depends on Bear's local database layout and therefore requires Bear and database access on macOS. It is not documented as a cloud connector or as a Windows or Linux integration. Database access permissions and the correct local path are prerequisites, especially for Docker mounts.

The documented feature set is limited to reading notes, searching note text, and listing tags. No authentication flow, API key, or remote endpoint is described. The project is released under the ISC license.

_Full upstream README: https://allmcps.com/mcp/akseyh-bear-mcp-server/readme_