How to Use the Bear MCP in AutoGen

Q: How do I register Bear MCP tools with an AutoGen agent?

Use the autogen-extmcp package to load the tools. Pass the resulting tool list to your AssistantAgent constructor, enabling them to call createnote and searchnotes during conversations.

Let your AutoGen agents debate, organize, and refine your Bear notes through multi-agent consensus.

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 AutoGen

Create your Vinkius account to connect Bear to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent debate over your Bear notes

Let your agents collaborate on your markdown files. One agent can draft content using `create_note`, while a critic agent reviews the text and suggests edits using `add_text` until they agree. This collaborative workflow ensures your notes are polished before you read them. Instead of a single agent making blind edits, you get a curated, reviewed document.

Consensus-driven tag cleanup with this MCP Server

Cleaning up tags requires careful planning. Your AutoGen agents can debate which tags to merge or delete using `list_tags`, and then safely execute `rename_tag` or `delete_tag` once they reach a consensus. A security agent can block accidental deletions of critical tags. This keeps your note organization intact and prevents automated scripts from ruining your taxonomy.

Automated note archiving and trashing

Let your agents manage the lifecycle of your documents. They can scan your workspace with `search_notes` and decide whether to run `archive_note` or `trash_note` on outdated files. Because the agents debate the status of each note, you do not have to worry about losing important work. They only archive files that meet all your criteria.

Setup guide

Set up Bear MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Bear tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Bear_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Bear data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Bear_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Bear data")
    print(result.messages[-1].content)

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 AutoGen

Use the `autogen-ext[mcp]` package to load the tools. Pass the resulting tool list to your `AssistantAgent` constructor, enabling them to call `create_note` and `search_notes` during conversations.

Yes, multiple agents can take turns editing. One agent can read the note with `open_note`, a second agent can propose additions, and a third can execute `add_text` to apply the final changes.

You can configure a supervisor agent to review all tag changes. Before executing `rename_tag` or `delete_tag`, the agent must get approval from the supervisor in the chat history.

The adapter supports both stdio and Streamable HTTP transports. You can easily connect your multi-agent system to our hosted MCP endpoint using the standard HTTP parameters.

The server runs in a secure, isolated sandbox environment. Your markdown notes, tags, and search queries are never stored or shared, keeping your personal knowledge base completely private.

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