MCP Bear, developed by Jkawamoto, is an archived server tool designed to connect AI assistants with the Bear note-taking application. This free, TypeScript-based program enables AI to interact with your notes, supporting various automation and management tasks. Its purpose was to bridge the gap between AI clients and Bear, allowing for enhanced interaction with note content and organization. The project is no longer actively maintained because Bear now includes its own native MCP server, making this standalone version obsolete for new deployments. It was distributed via downloadable MCP bundles from GitHub releases.

What does MCP Bear connect to?

MCP Bear functions as an MCP (Model Context Protocol) server, establishing a connection to the Bear note-taking application. It falls into the category of an MCP server specifically for note-taking apps, allowing AI assistants to interact with Bear notes. This interaction likely involves connecting to Bear's internal data, such as its SQLite database, primarily for read operations. The server acts as an intermediary, translating AI requests into actions within the Bear environment.

Core features and tools

This server wraps Bear's X-callback-url Scheme actions as callable tools for AI assistants. These include /open-note, /create, /add-text, /add-file, /tags, /open-tag, /rename-tag, /delete-tag, /trash, /archive, /untagged, /todo, /today, /locked, /search, and /grab-url. These tools allow AI clients to perform a variety of operations, from creating new notes to managing tags and searching note content.

Who is it for?

The audience for MCP Bear includes users interested in integrating AI assistants with their Bear notes. This integration supports automation and more dynamic interaction with their personal knowledge base. It allows for advanced queries and modifications to notes through AI commands. AI clients such as Claude are confirmed compatible with this server. Skip this if you prefer a native MCP server implementation within Bear.

How to get started

No credentials are required for MCP Bear to operate. Local MCP servers commonly communicate using stdio (standard input/output) for interaction with AI clients.

Use cases

• Searching for specific notes based on content or tags (e.g., "Find the deep-dive I wrote on export pipelines, somewhere under #engineering/").
• Modifying existing notes by appending or replacing text (e.g., "Append today's decisions to the 'Decisions' section of my Weekly Ops note").
• Managing tags across the note library (e.g., "Rename a tag across your whole library").

MCP Bear provided a valuable bridge for AI assistants to interact with Bear notes, offering tools for searching, modifying, and managing note content. Its free license and TypeScript foundation made it an accessible option for early AI integration. While superseded by native Bear functionality, it demonstrated the potential for AI-driven note management. Start by searching for specific notes using an AI assistant compatible with MCP Bear.