About Bear MCP Server
Bear MCP Server lets AI assistants read notes from the Bear note-taking app. It queries Bear’s SQLite database in strict read-only mode, with tools for notes and tags.
Key features
- 01Open notes by title or ID
- 02Search notes by term or tag
- 03List all Bear tags
- 04Show notes associated with a tag
- 05Read-only database access
Use cases
- 01Find notes about a topic
- 02Retrieve a note by its title
- 03Review tags and notes grouped by tag
MCP support
Exposes read-only Bear note and tag access to MCP clients through tools for opening and searching notes and browsing tags.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEBear MCP Server
A Model Context Protocol (MCP) server that allows AI assistants like Claude to read notes from the Bear note-taking app. This implementation connects directly to the Bear SQLite database in a read-only mode, ensuring your notes remain safe and unmodified.
Quick Start
Option 1: Install from GitHub (Recommended)
npx github:bart6114/my-bear-mcp-server
That's it! The server will start running and connect to your Bear database.
Option 2: Clone and Run Locally
# Clone the repository
git clone https://github.com/bart6114/my-bear-mcp-server.git
cd my-bear-mcp-server
# Install dependencies
npm install
# Build and run
npm run build
npm start
Prerequisites
- macOS with Bear app installed
- Node.js 18 or higher
Configuration
For Claude Desktop App
Add this to your configuration file at ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"bear": {
"command": "npx",
"args": ["github:bart6114/my-bear-mcp-server"],
"env": {},
"disabled": false,
"autoApprove": []
}
}
}
For Claude VS Code Extension
Add this to your configuration file at ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json:
{
"mcpServers": {
"bear": {
"command": "npx",
"args": ["github:bart6114/my-bear-mcp-server"],
"env": {},
"disabled": false,
"autoApprove": []
}
}
}
Available Tools
The Bear MCP server provides these read-only tools (all operations are non-destructive and cannot modify your Bear database):
open_note
Open a note by title or ID.
search_notes
Search for notes by term or tag.
get_tags
Get all tags in Bear.
open_tag
Show all notes with a specific tag.
Example Usage
Here are examples of how to interact with the Bear MCP tools through AI assistants:
Searching for Notes
Ask your AI assistant to search for notes containing specific terms:
Can you find all my notes about "project management"?
Opening a Specific Note
Ask your AI assistant to retrieve a specific note by title:
Show me my note titled "Meeting Notes - March 2025"
Viewing Tags
Ask your AI assistant to list all your Bear tags:
What tags do I have in my Bear notes?
Finding Notes with a Specific Tag
Ask your AI assistant to show notes with a particular tag:
Show me all notes with the #work tag
Advanced Options
If your Bear database is in a non-standard location:
npx github:bart6114/my-bear-mcp-server --db-path /path/to/your/database.sqlite
Technical Details
Read-Only Implementation
This MCP server connects to your Bear SQLite database using a strict read-only connection. This is enforced at the database driver level:
// From src/bear-db.ts
this.db = new Database(dbPath, { readonly: true });
This ensures that:
- No write operations can be performed on your database
- Your notes and tags cannot be modified, deleted, or corrupted
- The database connection will fail if write permissions are attempted
All operations performed by this server are SELECT queries that only retrieve data without modifying it.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.