How to Use the DBeaver (CloudBeaver) MCP in CrewAI

Q: How do I connect CrewAI agents to DBeaver (CloudBeaver)?

Pass your Vinkius MCP Server HTTP URL directly into the mcps parameter when defining your CrewAI agents. The framework automatically discovers tools like getconnectioninfo and assigns them to the correct agent.

Q: Can a CrewAI agent terminate database sessions in DBeaver (CloudBeaver) without human intervention?

Yes. An agent can call dbsmterminate to kill a hung session if you configure it to operate autonomously. For critical actions, you can set humanintheloop to require manual confirmation.

Q: How do CrewAI agents collaborate on DBeaver (CloudBeaver) configurations?

One agent can use getaisettings to inspect current server parameters, while a senior agent uses configureserver to apply updates. They share state using CrewAI's memory features to prevent conflicting changes.

Q: How does CrewAI handle team management inside the database manager?

Your agents use createteam and deleteteam to manage access groups. They can automatically assign connection rights to these teams using addconnectionsaccess based on corporate directory updates.

Deploy a crew of specialized CrewAI agents to manage DBeaver (CloudBeaver) database access using this MCP Server.

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 CrewAI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous User Provisioning and Audit

The `create_user` tool provisions new administrative accounts on your DBeaver (CloudBeaver) server, while `get_admin_user_info` retrieves detailed profile configurations. A CrewAI admin agent initiates the creation, and an audit agent verifies the permissions immediately after. This division of labor ensures that no user is created without proper verification. The agents coordinate using shared memory, keeping a clean log of all administrative actions without human input.

Track Compliance via CrewAI MCP Server

The `get_all_product_licenses` tool extracts server license details, and `get_driver_list` retrieves the active database drivers on your DBeaver (CloudBeaver) server. Your compliance crew monitors these endpoints to spot expired licenses or outdated database drivers. When an issue is found, the researcher agent identifies the missing driver while the manager agent queues an update. This keeps your central database portal compliant and fully functional.

Coordinate Large Data Exports Autonomously

The `data_transfer_export_data_from_container` tool starts background data exports, while `data_transfer_available_stream_processors` checks the available formats on your DBeaver (CloudBeaver) server. A specialized export agent triggers the transfer, and a delivery agent monitors the task until the file is ready. The crew handles the entire sequence from format validation to final verification. This allows your team to request complex reports and receive them without manual tracking of long-running database tasks.

Setup guide

Set up DBeaver (CloudBeaver) 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 DBeaver (CloudBeaver) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent DBeaver (CloudBeaver) 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="DBeaver (CloudBeaver) Analyst",
        goal="Access and analyze DBeaver (CloudBeaver) data via MCP.",
        backstory="Expert analyst with direct DBeaver (CloudBeaver) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent DBeaver (CloudBeaver) 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 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 CrewAI

Pass your Vinkius MCP Server HTTP URL directly into the `mcps` parameter when defining your CrewAI agents. The framework automatically discovers tools like `get_connection_info` and assigns them to the correct agent.

Yes. An agent can call `db_sm_terminate` to kill a hung session if you configure it to operate autonomously. For critical actions, you can set `human_in_the_loop` to require manual confirmation.

One agent can use `get_ai_settings` to inspect current server parameters, while a senior agent uses `configure_server` to apply updates. They share state using CrewAI's memory features to prevent conflicting changes.

Your agents use `create_team` and `delete_team` to manage access groups. They can automatically assign connection rights to these teams using `add_connections_access` based on corporate directory updates.

Absolutely. All user profiles, connection strings, and administrative metadata remain isolated. The Vinkius MCP Server runs in a secure, zero-trust environment, ensuring your credentials never leak during agent collaboration.

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