MCP Server

Maintained

MIT

io.github.jkawamoto/mcp-bear MCP Server

io.github.jkawamoto/mcp-bear

MCP server for Bear note-taking app (archived; Bear now has native MCP support)

What is the io.github.jkawamoto/mcp-bear MCP server?

The Bear MCP Server is a Model Context Protocol server that enables AI agents to interact with Bear note-taking software through actions like creating notes, searching, managing tags, and organizing content. This project is archived as of Bear v2.8, which includes native MCP server support.

This server allows Claude and other AI agents to read, create, and manage notes in Bear via MCP. It supports note operations (create, open, add text/files), tag management, searching, and organizing notes by status (todo, today, archived, locked). Note: Bear now includes native MCP support, making this standalone server unnecessary.

How to install io.github.jkawamoto/mcp-bear

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

Environment / auth

BEAR_API_TOKEN
required
secret
Bear API token

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp-bear": {
      "command": "https://github.com/jkawamoto/mcp-bear/releases/download/v0.5.2/mcp-bear.mcpb",
      "args": [],
      "env": {
        "BEAR_API_TOKEN": "<YOUR_BEAR_API_TOKEN>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

open-note — Open a note in Bear
create — Create a new note
add-text — Add or replace text in a note
add-file — Add a file to a note
tags — List or manage tags
open-tag — Open a specific tag
rename-tag — Rename an existing tag
delete-tag — Delete a tag
trash — Move note to trash
archive — Archive a note
untagged — Access untagged notes
todo — Access todo items
today — Access today's notes
locked — Access locked notes
search — Search notes
grab-url — Grab content from a URL into a note

Use cases

Create and organize notes in Bear from Claude conversations
Search and retrieve notes by tag or content
Manage note metadata like tags, archives, and todo status
Add files and web content to Bear notes
Automate note-taking workflows with AI assistance

io.github.jkawamoto/mcp-bear MCP server FAQ

What is the Bear MCP Server?

It's a MCP server that lets AI agents like Claude interact with Bear note-taking software. It supports creating notes, searching, managing tags, and organizing content.

Is this server still maintained?

No, this repository is archived. As of Bear v2.8, Bear includes a native MCP server implementation, making this standalone server unnecessary.

How do I install it in Claude?

Download the latest mcp-bear.mcpb file from the Releases page and open it in Claude Desktop's Settings window, or manually edit claude_desktop_config.json with the provided configuration.

What authentication is required?

You need a Bear API token, which should be set as the BEAR_API_TOKEN environment variable during installation.

Should I use this or Bear's native MCP server?

Use Bear's native MCP server (available in Bear v2.8+) instead, as this project is archived and no longer maintained.

What note operations are supported?

Create, open, search, add text/files, manage tags, archive, trash, and organize by status (todo, today, locked, untagged).

README (reference)

Source of truth, from the repository.

[!NOTE] This repository is archived. As of v2.8, Bear now includes a native MCP server implementation, making this standalone server unnecessary.

Bear MCP Server

A MCP server for interacting with Bear note-taking software.

Installation

[!NOTE] You'll need uv installed on your system to use uvx command.

goose

Open this link

goose://extension?cmd=uvx&arg=--from&arg=git%2Bhttps%3A%2F%2Fgithub.com%2Fjkawamoto%2Fmcp-bear&arg=mcp-bear&id=bear&name=Bear&description=Interacting%20with%20Bear%20note-taking%20software&env=BEAR_API_TOKEN

to launch the installer, then click "Yes" to confirm the installation. Set BEAR_API_TOKEN environment variable to your api token.

<details> <summary>Manually configuration</summary>

You can also directly edit the config file (~/.config/goose/config.yaml) to include the following entry:

extensions:
  bear:
    name: Bear
    cmd: uvx
    args: [--from, git+https://github.com/jkawamoto/mcp-bear, mcp-bear]
    envs: { "BEAR_API_TOKEN": "<YOUR_TOKEN>" }
    enabled: true
    type: stdio

</details>

For more details on configuring MCP servers in Goose, refer to the documentation: Using Extensions | goose.

Claude

Download the latest MCP bundle mcp-bear.mcpb from the Releases page, then open the downloaded .mcpb file or drag it into the Claude Desktop's Settings window.

<details> <summary>Manually configuration</summary>

You can also manually configure this server for Claude Desktop. Edit the claude_desktop_config.json file by adding the following entry under mcpServers:

{
  "mcpServers": {
    "bear": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/jkawamoto/mcp-bear",
        "mcp-bear",
        "--token",
        "<YOUR_TOKEN>"
      ]
    }
  }
}

After editing, restart the application.

</details>

For more information, see: Connect to local MCP servers - Model Context Protocol.

LM Studio

To configure this server for LM Studio, click the button below.

Actions Implemented

The server supports the following actions. Refer to Bear's X-callback-url Scheme documentation for details on each action.

License

This application is licensed under the MIT License. See the LICENSE file for more details.

Related MCP servers

io.github.jkawamoto/mcp-florence2

Active

An MCP server for processing images using Florence-2

Python

MIT

View repository →

io.github.jkawamoto/mcp-memos

Maintained

An MCP server for interacting with Memos.

Python

MIT

View repository →

io.github.jkawamoto/mcp-youtube-transcript

Active

Retrieve transcripts and metadata from YouTube videos with language support and pagination.

467

Python

MIT

View repository →

Austrian Firmenbuch

Maintained

Austria's official company register (Firmenbuch) – master data, financials & ratios for AI agents.

Python

MIT

View repository →

Handelsregister

Maintained

German Handelsregister + Austrian Firmenbuch for AI agents: master data, financials & ratios.

Python

MIT

View repository →

domscout

Active

domscout browser API as MCP tools: screenshots, Markdown, structured data, page automation, crawls.

JavaScript

MIT

View repository →