How to Use the Bear MCP in Mastra AI

Q: How do I build a Mastra AI workflow to clean up old Bear tags?

Start with the listtags tool to get all your current tags. Then, use Mastra's logic to identify which ones to change and call renametag or deletetag as needed. The workflow engine handles the looping and error checking.

Q: Can I get the full content of a note?

Yes, the opennote tool is for that. Give it a note ID, and it returns the complete Markdown content for your agent to process.

Build resilient, multi-step automations for your Bear notes using Mastra AI. Handle failures, retry operations, and build robust workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bear MCP to Mastra AI

Create your Vinkius account to connect Bear to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Bear with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Note Management

This MCP server's tools let your Mastra AI agent manage your Bear knowledge base. A workflow can `search_notes` for anything with an `@archive` tag, then loop through the results and call `archive_note` on each one. Mastra's engine means if one `archive_note` call fails, it won't kill the whole process. It can retry automatically or branch to a different step, like logging the error to a separate note with `create_note`.

Reliable Tag Re-organization

Cleaning up tags is a perfect job for an agent. You can build a Mastra workflow that uses `list_tags` to find old tags, then systematically renames them with `rename_tag`. If a rename operation fails, Mastra can automatically back off and try again. You can build a workflow that's guaranteed to finish the job, and this MCP Server gives your agent the tools it needs to execute those steps.

A Resilient MCP Server for Mastra AI

Combine Mastra AI's workflow engine with tools that act on your notes. An agent can try to `add_text` to a specific note. If the note ID is wrong and the tool fails, your workflow can catch the error, use `search_notes` to find the correct one, and then retry the `add_text` operation. This is what makes the combination powerful. You aren't just calling tools; you're building intelligent processes that can handle unexpected issues without needing you to step in.

Setup guide

Set up Bear MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Bear tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "bear-mcp-client",
  servers: {
    "bear-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Bear Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Bear tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Bear transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Bear. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Bear now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Bear MCP in Mastra AI

Start with the `list_tags` tool to get all your current tags. Then, use Mastra's logic to identify which ones to change and call `rename_tag` or `delete_tag` as needed. The workflow engine handles the looping and error checking.

Absolutely. You can set up a scheduled workflow that gathers information, formats it as Markdown, and then uses the `create_note` tool to add it to Bear each day.

The tool call will fail, but Mastra's workflow engine can catch that error. You can then program your agent to use `search_notes` to find a similar note or `create_note` to make a new one, making your automation much more robust.

Yes, the `open_note` tool is for that. Give it a note ID, and it returns the complete Markdown content for your agent to process.

Data privacy is critical. Your Bear note content and tag information are only processed in-memory within isolated, single-use sandboxes for the duration of a tool call. We don't log or persist any of your personal note data.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript