An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Bear to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn your local notes into an actionable brain for your AI.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Bear.

  1. 01

    Create note

    This capability starts a new native Bear note from scratch.

  2. 02

    Search notes

    Use this to find specific information across your entire Bear database.

  3. 03

    Trash note

    This moves a specific note directly into your Bear trash.

  4. 04

    Open tag

    This capability retrieves a list of all notes associated with a specific tag.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Bear.

  1. 05

    Add text

    This allows your agent to append or prepend markdown content to an existing note.

  2. 06

    Archive note

    This moves a note into your Bear archive to keep your main list clean.

  3. 07

    Delete tag

    This removes a specific tag from your entire Bear taxonomy.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Bear.

  1. 08

    List tags

    This capability pulls your full nested tag hierarchy so the agent understands your organization.

  2. 09

    Open note

    This fetches the complete markdown content of a single note for your agent to read.

  3. 10

    Rename tag

    This updates a tag name globally across every note where it is used.

Real work

What teams actually run

01

Code Snippet Injection

Pull a specific configuration block from a Bear note directly into your IDE.

02

Automated Organization

Ask your agent to clean up your tags or move old project notes to the archive.

03

Research Synthesis

Have your agent read multiple notes to summarize a specific topic.

04

Task Management

Search for the '@todo' tag to quickly find all pending items in your notes.

Automate a task

Put Bear to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Bear works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Bear to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

959ms average. Fast in production.

Bear is checked daily against the live service.

Daily averagePeak 1146ms
Oct 3Today
Fastest day
774ms
Slowest day
1146ms
14-day trend
Slowing+6%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Bear, so you can see the experience inside your AI.

It does not authenticate your account with Bear. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Bear Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_TLQxZBRzGLnr7TZkljxUEGdAXpbyLHKIFiqqZEvb/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Bear capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "bear-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_TLQxZBRzGLnr7TZkljxUEGdAXpbyLHKIFiqqZEvb/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Bear in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Bear owners hand off.

This is built for people who use Bear as their primary thinking capability and want to use AI to interact with that data.

  • 01

    Developers

    Inject saved code blocks from Bear directly into your active coding session.

  • 02

    Writers

    Let your agent read fragmented research notes to help assemble full drafts.

  • 03

    Researchers

    Organize complex, nested hierarchies of information using natural language.

FAQ

Questions Bear owners ask.

  • 01

    How does this MCP connect to my notes?

    You provide your Bear API Token, which allows the MCP to interface directly with your private Bear instance.

  • 02

    Which AI clients can I use with this?

    You can use any MCP-compatible client, including Claude, Cursor, and Windsurf.

  • 03

    Can the AI delete my notes?

    The agent can move notes to the trash or the archive using the provided capabilities, giving you control over your note lifecycle.

  • 04

    Does this work with my existing tags?

    Yes, the agent can list, rename, or delete tags to manage your note hierarchy.

  • 05

    Is my data secure?

    The MCP interfaces with your private Bear instance using your API token, ensuring your local knowledge base remains under your control.

  • 06

    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.

  • 07

    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.

  • 08

    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.

Explore

More in Productivity

Suggestions

Connect Bear to Claude, Cursor, ChatGPT & more