How to Use the Bear MCP in CrewAI

Q: How would I set up a CrewAI agent to automatically archive old Bear notes?

You'd give an agent the archivenote tool and a goal. For instance, its task could be to find all notes with a done tag using opentag and then call archivenote on each one sequentially.

Q: Can I have one CrewAI agent find notes in Bear and another agent edit them?

Definitely. The first agent uses searchnotes to find the target note ID. It passes that ID to the second agent, which then uses addtext to append or prepend new content.

Q: How does this MCP server handle Bear's nested tags for CrewAI?

The listtags tool provides the complete nested structure. An agent can parse this to understand the relationships, making it possible to build crews that perform complex reorganization based on your tag hierarchy.

Deploy autonomous teams of CrewAI agents to manage, research, and organize your Bear knowledge base without any human intervention.

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 CrewAI

Create your Vinkius account to connect Bear to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

A Research Crew for Your Notes

Assign roles to your CrewAI agents. A 'Researcher' agent can use `search_notes` and `open_tag` to find all relevant information on a topic within your Bear notes. It then passes those note IDs to the next agent. A 'Synthesizer' agent can take those IDs, use `open_note` to read the full content of each one, and compile a summary. Finally, a 'Writer' agent can use `create_note` to save that summary as a new, clean note in Bear.

Autonomous Note Curation

Set up a crew to keep your notes tidy. One agent can be tasked with finding notes tagged `#cleanup` by using `open_tag`. A second agent can read each note with `open_note` to decide if it should be archived or deleted. Based on that decision, the second agent delegates to an 'Archiver' agent which calls `archive_note`, or a 'Janitor' agent that uses `trash_note`. This whole process runs on its own. It's a true autonomous MCP integration.

Build Your Own Bear OS

Think bigger than just one-off tasks. With this MCP Server, you can build a persistent CrewAI team that acts like an operating system for your notes. Have an agent that constantly scans for new notes to tag, another that archives weekly, and a third that generates reports. They all share the same tools and memory, running 24/7.

Setup guide

Set up Bear MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Bear tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Bear Analyst",
    goal="Access and analyze Bear data via MCP.",
    backstory="Expert analyst with direct Bear access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Bear transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Bear Analyst",
        goal="Access and analyze Bear data via MCP.",
        backstory="Expert analyst with direct Bear access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Bear transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Yes, this is a perfect use case. One agent finds notes with `search_notes`, another reads them with `open_note`, and a third writes a new summary with `create_note`. CrewAI manages the collaboration between them.

You'd give an agent the `archive_note` tool and a goal. For instance, its task could be to find all notes with a `#done` tag using `open_tag` and then call `archive_note` on each one sequentially.

Definitely. The first agent uses `search_notes` to find the target note ID. It passes that ID to the second agent, which then uses `add_text` to append or prepend new content.

The `list_tags` tool provides the complete nested structure. An agent can parse this to understand the relationships, making it possible to build crews that perform complex reorganization based on your tag hierarchy.

Your note data, including Markdown content and tag lists, is handled with zero-trust principles. Each tool execution happens in a dedicated, ephemeral environment that is destroyed immediately after. Your note content is never written to disk on our side.

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