How to Use the DBeaver (CloudBeaver) MCP in LangChain

Q: How do I create a user and grant access in DBeaver (CloudBeaver) using LangChain?

Your agent would call the createuser tool first, then use the returned user ID in a subsequent call to addconnectionsaccess. It's a classic example of chaining tool outputs to inputs in LangChain.

Q: Can a LangChain agent check the server license for DBeaver (CloudBeaver)?

Yes. Just include the getactiveproductlicense and getallproductlicenses tools in your agent's toolset. It can then call them to get details on current or all installed licenses.

Q: How do I list all available database drivers in DBeaver (CloudBeaver) with LangChain?

Give your agent the getdriverlist tool. A simple call to that tool will return a complete list of all database drivers the CloudBeaver server supports.

Build database admin agents in LangChain. Chain commands to manage users, connections, and server configurations.

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 LangChain

Create your Vinkius account to connect DBeaver (CloudBeaver) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate User & Access Management

This isn't just about calling one tool. It's about building a sequence. Your LangChain agent can run `create_user` to provision a new account, immediately follow up with `create_team` to make a new group, and then use `add_connections_access` to grant the right database permissions—all in a single, automated chain. You define the logic, the agent executes the steps. This is how you automate onboarding. No more manual clicking through an admin UI. Just give your agent a goal, and it uses the DBeaver tools in the correct order to get it done.

Inspect and Manage Server State

Get your agent to troubleshoot for you. It can start by calling `get_driver_list` to see what's available, then use `get_connection_info` to check the status of a specific database connection. If it finds a problem, like a stuck process, the next link in the chain can be a call to `db_sm_terminate` to kill the session. It's a simple, logical flow that moves from diagnosis to resolution without any human intervention.

Build Data Export Chains with LangChain

Exporting data becomes a two-step agentic task. First, your agent uses `data_transfer_export_data_from_results` to package up the output from a specific SQL query you just ran. Alternatively, it can grab an entire table or schema with `data_transfer_export_data_from_container`. Your agent decides which tool is right for the job, then kicks off the async export task. This MCP Server gives you the building blocks for complex data pipelines.

Setup guide

Set up DBeaver (CloudBeaver) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes DBeaver (CloudBeaver) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "dbeaver-cloudbeaver-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent DBeaver (CloudBeaver) transactions"
    })
    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 LangChain

Your agent would call the `create_user` tool first, then use the returned user ID in a subsequent call to `add_connections_access`. It's a classic example of chaining tool outputs to inputs in LangChain.

Yes. Just include the `get_active_product_license` and `get_all_product_licenses` tools in your agent's toolset. It can then call them to get details on current or all installed licenses.

Use a chain. First, run your query. Then, pass the result set ID to the `data_transfer_export_data_from_results` tool. Your LangChain agent can handle the entire sequence.

Give your agent the `get_driver_list` tool. A simple call to that tool will return a complete list of all database drivers the CloudBeaver server supports.

This server only handles metadata like user credentials and connection strings, not your actual database content. Vinkius isolates every MCP tool call in an ephemeral sandbox, and all authentication is managed through a single, short-lived token. Your secrets aren't stored.

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