Reads Bear notes, searches note text, and lists tags through MCP on macOS.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
One-click editor setup isn’t available for this listing yet — we don’t have a confirmed install command, and we’d rather show nothing than point your editor at the wrong package or host. Follow the project’s own setup instructions, linked above.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Bear MCP Server.
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.
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.
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.
akseyh/bear-mcp-server MCP server supports three documented capabilities:
get_notes.get_notes_like.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.
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.
Factual signals from GitHub, npm, and our automated checks — not a rating.
No reviews yet — be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/akseyh-bear-mcp-server)<a href="https://allmcps.com/mcp/akseyh-bear-mcp-server"><img src="https://allmcps.com/api/badge/akseyh-bear-mcp-server?style=directory" alt="Bear MCP Server on AllMCPs" /></a>