How to Use the Databox MCP in Claude Code

Q: How do I add the Databox MCP Server to Claude Code?

Run claude mcp add --transport http databox -- https://vinkius.com/endpoint. Ensure you place all flags before the server name. Use claude mcp list to confirm the connection.

Q: How do I check which Databox account Claude Code is modifying?

Instruct the CLI to run the getcurrentuser tool. It returns the active profile and workspace details, preventing you from pushing test data into a production environment.

Pipe metrics straight into your terminal using the Databox MCP Server. Let Claude Code query datasets and push KPI data via headless CLI commands.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Databox MCP to Claude Code

Create your Vinkius account to connect Databox to Claude Code 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 Databox with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless Databox MCP Server Operations

Claude Code triggers the `push_metrics_data` tool directly from your terminal to automate metric ingestion inside CI/CD pipelines. You can drop a single command into a GitHub Action that reads test coverage results and fires them straight into a dashboard. No custom python scripts required. Managing these automated flows happens entirely via the CLI. If a nightly cron job starts failing, your terminal agent runs `list_activity_logs` to diagnose the exact HTTP errors. You fix the shell script and verify the fix without ever leaving the command line.

Audit Storage and Usage Instantly

The `get_storage_statistics` tool allows your terminal agent to pull hard numbers on your data consumption. When your DevOps team needs to know why the analytics bill spiked, Claude Code grabs the exact row counts and storage volumes across all workspaces. Digging deeper into specific containers takes one prompt. The agent executes `get_dataset_details` to show you the exact schema and update frequency of any metric block. You get raw JSON output piped straight to your screen for fast inspection.

Provision Datasets from the Command Line

Your AI client calls `create_data_source` to spin up fresh ingestion endpoints while you configure a new server. As you deploy a new backend service, the agent simultaneously creates the required analytics infrastructure to monitor it. Cleaning up the environment requires zero manual clicks. Tell the CLI to wipe out the staging metrics, and it fires off `delete_dataset` for every test container you built that week. The operation finishes before a browser tab could even load.

Setup guide

Set up Databox MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see databox-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Databox transactions." It will automatically discover and invoke the available Databox tools.

Terminal

claude mcp add --transport http databox-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Databox MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "databox-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Databox. 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 Databox 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 Databox MCP in Claude Code

Run `claude mcp add --transport http databox -- https://vinkius.com/endpoint`. Ensure you place all flags before the server name. Use `claude mcp list` to confirm the connection.

The CLI client operates perfectly in headless modes like Docker containers or GitHub Actions. Pass your prompt via standard input to trigger dataset reads or metric pushes automatically.

The tool accepts raw JSON arrays matching the target schema. Your terminal agent will automatically format your local log data into the correct payload structure before sending it.

Instruct the CLI to run the `get_current_user` tool. It returns the active profile and workspace details, preventing you from pushing test data into a production environment.

Every request routes through a V8 Isolate Sandbox managed by Vinkius. Your API activity logs, storage metrics, and raw data payloads exist only in ephemeral memory. The entire environment is destroyed immediately after the execution completes.

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