How to Use the DBeaver (CloudBeaver) MCP in AutoGen

Q: How can I set up two AutoGen agents to manage users in DBeaver (CloudBeaver)?

Assign the createuser and deleteuser tools to an 'Admin' agent. Then, create a 'Security' agent that reviews the Admin's proposed plan. The conversation ensures no user is added or removed from DBeaver (CloudBeaver) without a check.

Q: Can one AutoGen agent propose a server change in DBeaver (CloudBeaver) and another approve it?

Yes, this is a core AutoGen pattern. One agent calls configureserver and presents the plan. The other agent can use tools like getconnectioninfo to check the potential impact on DBeaver (CloudBeaver) before approving.

Q: Is it possible for AutoGen agents to debate terminating a database session from DBeaver (CloudBeaver)?

Definitely. An agent can propose using dbsmterminate. A second agent can then argue against it, using data from getadminuserinfo to see who owns the session. They'll only proceed once they agree.

Q: How do I give AutoGen tools to interact with my DBeaver (CloudBeaver) server?

You use the mcpservertools function from the AutoGen extension, pointing it at your Vinkius MCP endpoint. It automatically fetches all 19 tools and makes them available to your agents.

Let AI agents debate and manage your DBeaver (CloudBeaver) server. Set up multi-agent conversations for safer database administration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DBeaver (CloudBeaver) MCP to AutoGen

Create your Vinkius account to connect DBeaver (CloudBeaver) 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 DBeaver (CloudBeaver) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven User Management

Set up a team of agents to handle user administration. One agent, the 'Provisioner', can suggest creating an account using the `create_user` tool. It doesn't execute the command immediately. Instead, a second 'Auditor' agent reviews the request. It can check existing users or team policies before giving the go-ahead. Only after the agents reach a consensus is the new user actually created. This conversational approach prevents mistakes.

Collaborative Server Maintenance

Imagine one agent notices a long-running query and proposes killing the connection with `db_sm_terminate`. This could be risky. With AutoGen, you can require a second agent to double-check the situation. The 'Analyst' agent can use `get_connection_info` to investigate the session's activity and `get_active_user` to see who it belongs to. The agents debate whether terminating the session is the right call, providing a layer of safety before taking action.

Debate Server Changes with AutoGen

Changing server configuration is a big deal. Have an 'Operator' agent propose a change using `configure_server`. Before it's applied, a 'Compliance' agent can step in to verify the change is valid. The Compliance agent might use `get_active_product_license` to ensure the new feature is supported by the current license, or `get_auth_providers` to check security implications. The change only happens after the agents agree, turning a risky manual task into a supervised, automated conversation. This MCP Server gives them the tools they need to have that debate.

Setup guide

Set up DBeaver (CloudBeaver) 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 DBeaver (CloudBeaver) 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="DBeaver (CloudBeaver)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent DBeaver (CloudBeaver) 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="DBeaver (CloudBeaver)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent DBeaver (CloudBeaver) 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 CloudBeaver. 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 DBeaver (CloudBeaver) 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 DBeaver (CloudBeaver) MCP in AutoGen

Assign the `create_user` and `delete_user` tools to an 'Admin' agent. Then, create a 'Security' agent that reviews the Admin's proposed plan. The conversation ensures no user is added or removed from DBeaver (CloudBeaver) without a check.

Yes, this is a core AutoGen pattern. One agent calls `configure_server` and presents the plan. The other agent can use tools like `get_connection_info` to check the potential impact on DBeaver (CloudBeaver) before approving.

Definitely. An agent can propose using `db_sm_terminate`. A second agent can then argue against it, using data from `get_admin_user_info` to see who owns the session. They'll only proceed once they agree.

You use the `mcp_server_tools` function from the AutoGen extension, pointing it at your Vinkius MCP endpoint. It automatically fetches all 19 tools and makes them available to your agents.

The server provides access to administrative data, such as team permissions and user access rights. Your actual database content is never touched. Vinkius proxies all requests, and authentication is handled by a single token, so your agents never handle raw credentials.

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