Bear Connector for AI agents.
10 live capabilities
Manage your markdown notes and research database with natural language.
Waiting for input…
Why people use Bear
Bear for Markdown Knowledge Management
This Connector changes that by letting your agent reach into your Bear database. You can ask it to find a specific note, read the full content, or even update your tags. It turns your static notes into a dynamic resource you can query and manipulate instantly.
What Vinkius changes
Your agent gets full read and write access to your Bear notes for instant information retrieval and organization.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Summarizing research archives
A researcher has 50 notes on 'Quantum Computing' and needs a summary.
- Real-world use case 02
Bulk renaming project tags
A dev needs to rename a project tag from 'Old_App' to 'Legacy_App'.
- Real-world use case 03
Injecting snippets into drafts
A writer wants to add a new paragraph to a draft.
Complete set · 10capabilities
The complete Bear capability set.
These are the exact actions your AI can choose when you ask it to work with Bear.
01—04
4 capabilities in this set.
Part of 10 available through Bear.
- 01 Capability
Search notes
Search across all Bear app notes. This finds notes based on content, titles, or specific tags like @todo.
- 02 Capability
Create note
Create a new native Bear note. This lets your agent start a new document with a title and specific tags.
- 03 Capability
Add text
Append or prepend Markdown chunks to a Bear note. This lets you add info to a note without overwriting what is already there.
- 04 Capability
Trash note
Move an explicit Bear Note to the Trash. Use this to clean up your workspace by removing discarded drafts.
05—07
3 capabilities in this set.
Part of 10 available through Bear.
- 05 Capability
Archive note
Archive an explicit Bear Note. This moves notes out of your active view while keeping them searchable.
- 06 Capability
List tags
Retrieve the exact Tags taxonomy nesting globally. This helps your agent understand your folder-like tag structure.
- 07 Capability
Open tag
List all explicit Bear notes matching a specific tag. Use this to quickly see every note related to a specific topic.
08—10
3 capabilities in this set.
Part of 10 available through Bear.
- 08 Capability
Rename tag
Rename globally an entire tag across all mapped Notes. This fixes taxonomy issues across your whole library instantly.
- 09 Capability
Delete tag
Destroy entirely a Tag constraint globally. Use this to remove tags that are no longer needed in your system.
- 10 Capability
Open note
Retrieve explicit complete Markdown content of a Bear note. This gives your agent the full text of a note to analyze.
Set up in minutes
One URL. Then ask Bear to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Bear from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_TLQxZBRzGLnr7TZkljxUEGdAXpbyLHKIFiqqZEvb/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Bear, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Bear for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_TLQxZBRzGLnr7TZkljxUEGdAXpbyLHKIFiqqZEvb/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Bear URL.
- Step 03
Save and start
Save the connection and enable Bear in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"bear": {
"url": "https://edge.vinkius.com/vk_preview_TLQxZBRzGLnr7TZkljxUEGdAXpbyLHKIFiqqZEvb/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Bear
Open Agent mode in chat and ask: "Using Bear, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"bear": {
"url": "https://edge.vinkius.com/vk_preview_TLQxZBRzGLnr7TZkljxUEGdAXpbyLHKIFiqqZEvb/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Bear
Ask Copilot: "Using Bear, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"bear": {
"url": "https://edge.vinkius.com/vk_preview_TLQxZBRzGLnr7TZkljxUEGdAXpbyLHKIFiqqZEvb/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Bear
Open Cascade and ask: "Using Bear, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"bear": {
"url": "https://edge.vinkius.com/vk_preview_TLQxZBRzGLnr7TZkljxUEGdAXpbyLHKIFiqqZEvb/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Bear
Ask Cline: "Using Bear, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add bear --transport http "https://edge.vinkius.com/vk_preview_TLQxZBRzGLnr7TZkljxUEGdAXpbyLHKIFiqqZEvb/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Bear
Ask Claude: "Using Bear, show me...". 10 tools are ready
Where the request belongs
Work Bear can move forward.
This is for anyone who treats Bear as their second brain but struggles with the friction of manual organization. It is for researchers with hundreds of tags and developers who store snippets in markdown.
Research Scientist
Summarizing months of scattered notes into a single cohesive draft.
Software Engineer
Pulling specific configuration blocks into a coding environment.
Content Strategist
Organizing nested tags and moving old projects to archives.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsOneNote
Connect your AI agent to Microsoft OneNote to search, read, extract, and append content to your personal or enterprise notebooks seamlessly.
Craft (Docs & Notes)
Manage collaborative docs via Craft.do. list documents, handle blocks, track tasks, and retrieve daily notes directly from any AI agent.
Mem AI (Knowledge Workspace)
Manage your knowledge base via Mem.ai. create notes, run AI semantic search, and organize collections.
Simplenote
Manage your Simplenote notes directly from your AI assistant. Create, search, edit, and organize plain-text notes without leaving the conversation.
Memo Meister
Create and organize smart notes with AI-powered tagging, search, and knowledge connections that make your ideas retrievable.
Logseq (Knowledge Management)
Manage your knowledge base via Logseq. create pages, insert outliner blocks, and search across your local graph.
Bring your own AI
Change the model, client or framework. Keep Bear connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Bear.
The practical details behind the request, access and result.
Can the Bear MCP read my full notes?
Yes, it can fetch the full markdown content of any specific note. This allows your agent to analyze the entire document to answer questions or summarize information.
Will this Connector help me organize my tags?
Absolutely. It can rename tags globally across your entire library, allowing you to fix taxonomy issues in one step instead of editing every note manually.
Can I use Bear MCP to move notes to the archive?
Yes, you can command your agent to move specific notes to the archive or trash. This helps keep your active workspace clean of old research or drafts.
How does Bear MCP handle new notes?
Your agent can create new native Bear notes for you. You just tell it what the title should be and what tags to apply, and it handles the creation instantly.
Can the Bear MCP search for specific tags?
Yes, it can search your entire Bear app for notes matching specific tags. This makes it easy to find all notes related to a specific project or topic.
Is my Bear data safe with this Connector?
The Connector connects directly to your private local instance using your Bear API Token. Your data remains private and is only accessed by your agent when you give it instructions.
Can the AI precisely update a note without overwriting its entire content?
Yes. It uses the add_text mutation capability, 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.
One connection away
Give your agent a direct line to Bear.
Connect Bear once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available