Bear

MCP server for reading Bear notes
  • typescript

1

GitHub Stars

typescript

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "quanticsoul4772-bear-mcp": {
      "command": "node",
      "args": [
        "--max-old-space-size=4096",
        "--expose-gc",
        "--max-semi-space-size=64",
        "/Users/yourusername/Projects/mcp-servers/bear-mcp/dist/index.js"
      ]
    }
  }
}

You can run a local MCP server that gives you programmatic access to your Bear notes, enabling AI assistants to search, read, and modify your Bear data through a consistent, scriptable API delivered over stdio.

How to use

You run the Bear MCP server locally and connect your MCP client to it via stdio. Use the provided tool endpoints to read notes, search by terms or tags, open notes by title or ID, manage tags, and perform write operations like creating notes or updating text. You can also move notes to trash, rename or delete tags, and retrieve statistics or recent items. The server keeps Bear data private to your machine and exposes a small set of well-defined operations that your client can invoke.

How to install

Prerequisites you need before installation:

  • Node.js 18 or higher

  • Bear app installed on macOS

Step-by-step commands to install the Bear MCP Server from source:

# Clone the repository
git clone https://github.com/quanticsoul4772/bear-mcp
cd bear-mcp

# Install dependencies
npm install

# Build the project
npm run build

# Install globally
npm link

Additional configuration and notes

To run the server with Claude Desktop or another MCP client, you typically point the client at a local stdio process that starts the server. The following examples show a common setup used to launch the Bear MCP server from Node with the built artifact at a standard path.

{
  "mcpServers": {
    "bear-mcp": {
      "command": "node",
      "args": [
        "--max-old-space-size=4096",
        "--expose-gc",
        "--max-semi-space-size=64",
        "/Users/yourusername/Projects/mcp-servers/bear-mcp/dist/index.js"
      ],
      "type": "stdio"
    }
  }
}

Custom database path

If your Bear database is stored in a non-standard location, specify the path with an additional argument when starting the server.

{
  "mcpServers": {
    "bear-mcp": {
      "command": "node",
      "args": [
        "--max-old-space-size=4096",
        "--expose-gc",
        "--max-semi-space-size=64",
        "/path/to/bear-mcp/dist/index.js",
        "--db-path",
        "/custom/path/to/database.sqlite"
      ],
      "type": "stdio"
    }
  }
}

Available tools and example usage

The server exposes a set of tools to interact with Bear data. Each tool corresponds to a specific capability you can invoke from your MCP client.

Troubleshooting

If you encounter issues, verify Bear is installed and the database is accessible. Common checks include ensuring the Bear database file exists and that the MCP process has read access to it.

Security considerations

This server runs locally via stdio and is not exposed over the network. Trashed notes are automatically excluded from results to avoid leaking unwanted data.

Available tools

open_note

Open a specific Bear note by its title or unique ID.

search_notes

Search for notes containing specific terms or tags.

get_tags

List all tags used in Bear notes, organized by frequency.

open_tag

Display all notes that have a specific tag.

get_recent_notes

Get recently modified notes.

get_pinned_notes

Get all pinned notes.

get_note_stats

Get statistics about your Bear notes.

get_notes_by_date

Get notes within a specific date range.

create_note

Create a new note in Bear.

add_text

Add text to an existing note (append, prepend, or replace).

trash_note

Move a note to trash.

rename_tag

Rename a tag across all notes.

delete_tag

Delete a tag from all notes.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational