mcp-bear: Connect AI Clients to Bear Notes
Summary
mcp-bear is a Python MCP server that lets compatible AI clients interact with Bear notes through Bear’s X-callback-url actions. It is archived and is largely superseded by Bear’s built-in MCP server.
At a glance
- Language
- Python
- License
- MIT
- Stars
- 77
- Forks
- 12
- Added to OSRepos
- February 14, 2026
- Last analyzed
- October 4, 2026
This repository is archived on GitHub and no longer maintained.
View on GitHubTopics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Overview
mcp-bear connects MCP-compatible clients to Bear, the macOS note-taking app. It exposes selected Bear actions so an AI assistant can search, open, create, and otherwise work with notes and tags.
The project is most relevant to users who need a bridge for clients that do not use Bear’s native MCP server. The repository is archived, and Bear now includes a native implementation, so the standalone server is generally unnecessary for current setups.
Key Features
- Provides an MCP server for interacting with Bear.
- Supports searching for and opening notes.
- Supports creating notes and partially adding text.
- Offers actions for tags, including listing, opening, renaming, and deleting tags.
- Exposes Bear actions for trash, archive, untagged, todo, today, and locked notes.
- Supports adding files and grabbing URLs.
- Can be configured with clients including Goose, Claude Desktop, and LM Studio.
Use Cases
- Bear users connecting an MCP-compatible assistant to notes for search and retrieval.
- Goose users who want to invoke Bear actions from an MCP extension.
- Claude Desktop users who need an existing bridge to Bear, particularly with an older Bear setup.
- Developers evaluating how Bear’s X-callback-url actions can be exposed through MCP.
Project Facts
- Language: Python
- License: MIT
- Stars: 77
- Forks: 12
- Topics: bear, macos, mcp-server, python, x-callback-url
- Archived: Yes
Getting Started
The README describes client-specific setup. For a compatible setup using uvx, the server can be launched from the GitHub repository:
uvx --from git+https://github.com/jkawamoto/mcp-bear mcp-bear --token <YOUR_TOKEN>
See the README for client configuration and details on the Bear API token.
Considerations
- The repository is archived. Bear’s native MCP server, available as of Bear 2.8, makes this standalone server unnecessary for many users.
- It requires Bear, a Bear API token, and
uvfor the documenteduvxsetup. - The
/add-textaction is only partially implemented, through thereplace_noteandadd_titlemethods. - The server works through Bear’s X-callback-url actions, so its capabilities follow the supported actions listed in the README.
Found this useful?
Share it with someone who would like mcp-bear.
Source repository
Open the original repository on GitHub.
11 counted GitHub visits
Related repositories
Similar repositories that may be relevant next.
omnigent: Orchestrate AI Coding Agents Across Harnesses
October 5, 2026
Omnigent provides a shared orchestration layer for AI coding agents, with policies, sandboxing, and team collaboration. It suits developers who want to combine agent runtimes and access sessions across devices without tying workflows to one harness.
agentevals: Evaluate AI Agents from OpenTelemetry Traces
October 4, 2026
agentevals scores AI agent behavior from existing OpenTelemetry traces, without rerunning agents or making extra model calls. It suits teams building instrumented agents that need local evaluation, golden-set checks, or CI quality gates.
web-design: Create Consistent Web Pages with a Claude Code Skill
October 3, 2026
web-design is a Claude Code skill that turns product briefs, reference URLs, or screenshots into an editable design specification before generating web code. It is suited to developers and designers who want a repeatable, spec-led workflow for building consistent pages.
oomwoo: Build a DIY Robot Vacuum
October 2, 2026
OOMWOO is a planned, hackable robot vacuum built around Raspberry Pi, ROS2 and 2D LiDAR. It is aimed at makers who want to build and customize a locally controlled vacuum, but its hardware and build instructions are still in development.