Databox MCP

Created By
Databox3 months ago
Connect your AI tool to your business data. Databox MCP lets AI agents query metrics, analyze performance, and generate insights from your connected data sources - all through natural conversation. Perfect for founders, marketers, and analysts who want data answers faster.
Overview

What is Databox?

Databox is a business analytics platform that connects 100+ data sources and makes your KPIs accessible through AI. With Databox MCP, AI agents can query live metrics, analyze performance, and generate insights — all through natural conversation.

Perfect for founders, marketers, and analysts who want data answers faster.

Learn more here: https://databox.com/mcp

How to use Databox MCP?

To use Databox MCP, connect your Databox account using your API token. Once connected, you can ask your AI tool questions about your business data — from marketing performance to revenue trends — without building dashboards or writing queries.

Key features of Databox MCP?

  • Query live metrics from 100+ integrations (Google Analytics, HubSpot, Stripe, and more)
  • Analyze trends, anomalies, and correlations across data sources
  • Generate reports and insights through natural language prompts
  • Access KPIs and dashboards without leaving your AI tool
  • Ingest and push custom data into Databox

Use cases of Databox MCP?

  • Marketing performance analysis across channels
  • Revenue and sales reporting for founders and operators
  • Cross-platform data comparison (e.g. ad spend vs. pipeline vs. revenue)
  • Automated weekly/monthly reporting through AI prompts

FAQ

What is required to set up Databox?

You need a Databox account and an API token. Get your token at app.databox.com/account/profile.

Which data sources does Databox support?

Databox connects to 100+ integrations including Google Analytics, HubSpot, Stripe, Facebook Ads, Shopify, and more.

Can I query real-time data?

Yes, Databox MCP queries live data from your connected sources so insights are always up to date.

Server Config

{
  "mcpServers": {
    "databox": {
      "command": "npx",
      "args": [
        "-y",
        "@databox/mcp-server"
      ],
      "env": {
        "DATABOX_API_TOKEN": "your-api-token"
      }
    }
  }
}
Project Info
Created At
3 months ago
Updated At
3 months ago
Author Name
Databox
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

2 days ago