# Bear MCP for AI Agents MCP > Bear MCP lets your AI agent manage your entire local markdown knowledge base. Instead of opening Bear and manually searching for notes or tags, you simply ask your AI client to find, edit, organize, or archive any piece of saved content—whether it's a code snippet from years ago or research notes. ## Overview - **Category:** productivity - **Price:** Free - **Tags:** markdown, personal-knowledge-base, document-management, offline-storage, text-editing ## Description Your personal knowledge vault is in Bear App, but accessing it used to mean context switching and manual searching. This connector links your private local markdown data directly to any AI agent, letting you treat your entire archive like one big searchable document. It handles everything from finding specific pieces of text across thousands of notes to restructuring your tags or creating entirely new drafts based on fragmented thoughts. If you're already using an advanced AI client and want it to actually *do* something with the massive amounts of writing, research, and code snippets you collect, this is it. Connecting through Vinkius means you get access to this Bear integration right alongside thousands of other tools your agent can use. Think of it like having a hyper-efficient librarian who knows every corner of your digital filing cabinet and doesn't need you to tell them where to look. ## Tools ### search_notes Searches across all your Bear app notes for specified keywords, tags, or dates. ### open_note Retrieves and displays the full Markdown content of a specific note by its ID. ### create_note Creates a completely new, blank note within your Bear App vault. ### add_text Appends or prepends raw markdown text chunks to an existing note's content. ### trash_note Moves a selected Bear Note directly into the Trash bin. ### archive_note Removes an explicit Bear Note from active view and places it in the Archive section. ### list_tags Retrieves a complete map of your tags, showing their full nested parent/child taxonomy structure. ### open_tag Lists all Bear notes that specifically match one or more provided tags. ### rename_tag Globally changes the name of a tag, updating every note using it automatically. ### delete_tag Completely removes a specific tag constraint from your entire knowledge base. ## Prompt Examples **Prompt:** ``` Find all notes tagged #todo from last month mentioning 'database'. ``` **Response:** ``` **✅ Found 3 relevant action items:** * **[Due: May 20th]** Re-evaluate user onboarding flow. (Source: UUID: ABC1...) * **[Urgent]** Draft initial API specs for migration. (Source: UUID: XYZ4...) * **[Review]** Check legacy data access points. (Source: UUID: PQR9...) Would you like me to open the full markdown content of the 'API specs' note so you can copy the details? ``` **Prompt:** ``` What tags do I have for product launch planning? ``` **Response:** ``` **📚 Bear Tag Taxonomy Map:** The current structure includes: * `#project/launch` (Parent) * `#project/launch/marketing` (Child) * `#project/launch/devops` (Child) * `#work/meetings` (Parent) * `#work/meetings/v2` (Child) Let me know if you want to see all notes under a specific branch. ``` **Prompt:** ``` Create a new draft note for the 'Phoenix' project and tag it #project/phoenix ``` **Response:** ``` ✅ Success. The note titled 'Project Phoenix Draft - 2026-07-15' has been created in your vault. It is already tagged with `#project/phoenix`. You can now start adding text or details to this new location. ``` ## Capabilities ### Search across all notes Quickly finds specific information or topics mentioned in any Bear note. ### Read full markdown content Pulls the complete, raw text and formatting of a selected Bear note for review. ### Create new knowledge items Generates and saves brand-new notes directly into your local Bear App vault. ### Edit existing content Adds or changes text blocks within a note without you having to copy and paste manually. ### Manage the archive and trash Moves old notes out of circulation, either into the Archive or permanently deleting them. ### Structure and modify tags Lists tag hierarchies, finds specific notes by tag, renames a tag across all relevant documents, or deletes an entire tag constraint. ## Use Cases ### Finding an old code snippet for a client meeting A developer needs to reference a specific API implementation from last year. They ask the agent to search their notes for 'API endpoint /user'. The tool uses `search_notes` and returns the relevant document, which they then open using `open_note` to pull the exact code block. ### Cleaning up a massive research folder A researcher finishes a topic. They ask the agent to identify all notes related to 'Pre-Columbian history' and archive them, while also confirming that any abandoned draft notes are moved to trash using `trash_note`. ### Standardizing project names across documentation A team lead notices the tag '#project/v1' is used inconsistently. They instruct the agent to globally rename it to '#project/legacy', ensuring all notes are updated via `rename_tag`. ### Drafting a meeting summary from scattered ideas A writer has several fragmented thoughts saved in different places. They ask the agent to collect all notes tagged 'work/meetings' and then use `add_text` to compile them into one cohesive draft. ## Benefits - You don't lose focus when your agent handles the research. Instead of manually opening Bear to find old snippets, you just ask it to pull them up for context. - Managing tags becomes instant. If you need to rename a project tag across hundreds of notes, the `rename_tag` tool updates everything globally in one step. - Writing drafts is faster because the agent can inject raw saved content directly into your document using `add_text`, eliminating copy/pasting friction. - Your archive stays clean. You use the MCP to automatically move outdated research into the Archive or Trash, keeping only actionable items visible. - The system gives you a full picture of your knowledge structure by listing all tags and their relationships via `list_tags` before you even start writing. ## How It Works The bottom line is, you tell the AI what you need done with your knowledge base, and it handles the connection details to execute the action. 1. Subscribe to this MCP and provide your Bear API Token. This lets the AI client talk directly to your local instance. 2. Use your preferred agent (like Claude or Cursor) to give a natural language command, such as 'Find all notes tagged #todo related to Q1'. 3. The agent executes the query against your vault and presents the results—whether that's opening a full note for review or confirming a tag was successfully renamed across thousands of items. ## Frequently Asked Questions **Can the AI precisely update a note without overwriting its entire content?** Yes. It uses the `add_text` mutation tool, seamlessly attaching blocks of text to either the absolute bottom (append) or the explicit top (prepend) of the given UUID note, leaving the core intact. **Does it understand nested tags (like #work/design/logo)?** Bear relies heavily on tagging workflows. The agent natively queries and navigates explicit sub-tag pathways exactly like the application UI, mapping out your distinct taxonomy rules efficiently. **Can it search for uncompleted action items across many notes?** Simply ask the agent to search for the specialized string '@todo'. Bear exposes these native markers directly via the API, returning every unique UUID containing a matching string checklist efficiently.