Databox
Pricing

Figma

Figma MCP Connector for Databox

Connect Figma to your AI Analyst through MCP. It reads the design files behind your product metrics, so it explains a shift with the real design, not just a number. Figma's MCP server is gated to approved clients today.

A Signup Conversion Rate card at 4.8%, up 12.4% vs last month, and under it why it happened: Conversion rose after the Sept 12 signup redesign - the new form cuts two fields.

TL;DR

Get more context from your Figma data

  • Same MCP server, wired into Databox. The Figma connector links Figma's own MCP server to your AI Analyst, added as a Custom connector since access is still gated to approved clients.
  • More than the numbers: your AI Analyst reads the actual design file, frame, or comment behind a product metric, not just a change in a number.
  • Sharper answers: it can explain a shift in engagement or conversion using the real design change, not a guess.

How to use it

Step 1

Open connector settings

Go to your AI Analyst settings → Connectors.

Step 2

Add a custom connector

Select Add custom connector, name it Figma and paste the URL of Figma's official MCP server.

Step 3

Authenticate with Figma

Sign in with your Figma account and set tool permissions per tool.

Step 4

Ask anything

Ask a question that touches Figma - it now pulls the record behind the number automatically.

More about it

The story

Landing page conversion drops, and it's tied to a redesign

Your AI Analyst spots the drop on your conversion databoard, then pulls up the exact Figma frame that shipped that week, so the dashboard and the design agree on what changed.

Feature engagement stalls after a UI change

Your AI Analyst matches the flatline on your product engagement databoard to the Figma file, showing which component changed and when, not just that usage stopped growing.

Confirming what's actually live before reporting a win

Before reporting a conversion lift on the dashboard, your AI Analyst checks Figma to confirm which variant is live, so the number and the design match.


Example prompts


Specs

AuthOAuth 2.0 (Figma authorization flow)
MCP serverhttps://mcp.figma.com/mcp
Dev docsdevelopers.figma.com/docs/figma-mcp-server

The Databox difference

Why connecting MCP through Databox is different

You can connect this same MCP server directly to any AI tool. Here’s what changes when you connect it through Databox instead.

Any AI tool

One AI tool, Claude here, on one MCP server, which reaches Asana, Slack and HubSpot and nothing else.

One tool, limited to MCP data

  • Only sees what this MCP server exposes, nothing more
  • No connection to your CRM, chat, or revenue data
  • Not wired into your business context, so nothing runs automatically

With Databox

Databox joining that same MCP server to its own integrations: Facebook Ads, Google Analytics, Stripe, Salesforce and HubSpot.

Enriched data, the whole story

  • The MCP connector brings in this data, same as anywhere else
  • Plus your other Databox integrations, already connected
  • Your AI Analyst reasons over the whole story, not just this one tool
  • Runs automatically with Routines, reusable in every Skill

Related

More like this

Canva

Design

Ask your AI Analyst about the design behind the metric, straight from Canva.

Ahrefs

SEO

See the backlink and site audit detail behind an SEO metric, straight from Ahrefs.

Airtable

Productivity

See the record and base behind an operations metric, straight from Airtable.

FAQ

Frequently asked questions

Is there an official Figma MCP server?

Yes. Figma runs its own remote MCP server at mcp.figma.com. Access is currently limited to a list of approved AI clients, with a waitlist for others.

Does connecting Figma cost extra?

No. MCP connectors are included with your AI Analyst on every plan that includes it.

Does it work with ChatGPT and Cursor?

Figma's MCP server supports the clients on its own approved list, which includes tools like Claude Code, Cursor, and VS Code. Check Figma's current list before connecting.

Is my Figma data secure?

Figma's MCP server uses OAuth, so your AI Analyst only sees what your Figma account already has access to, and you can revoke access at any time from your Figma account settings.

What is an MCP connector?

An MCP connector links your AI Analyst to an external tool through the Model Context Protocol, an open standard for connecting AI assistants to real business systems. Once connected, your AI Analyst can read (and soon act on) the records behind your metrics - deals, tickets, conversations, campaigns - without you switching tabs.

How is an MCP connector different from a Databox integration?

A Databox integration brings your metrics into Databox so you can track, visualize and report on them. An MCP connector gives your AI Analyst access to the records behind those metrics - the deal, the ticket, the ad, the Slack thread - so it can explain why a number moved and act on it in that tool. Many tools, like HubSpot and Facebook Ads, have both, and they work best together: the integration shows what changed, the connector shows why.

Can I connect any tool, or only the ones in the connector library?

Any tool with an MCP server. You can pick an official connector built by Databox, then click connect and sign in. Or you can add a custom connector: paste the server URL, choose how it signs in (OAuth, API key, bearer token or none), name it and connect.

Is my data safe when I connect a custom MCP server?

You decide what each connector can do. Every tool on a connector has its own setting - Always allow, Needs approval or Blocked - and every tool starts on Needs approval. Official connectors are reviewed by Databox. Custom servers are not, and once connected, a server can access your AI Analyst's content and share data outside Databox. Only connect servers you trust. You can change permissions or disconnect at any time.

Do MCP connectors cost extra?

No. MCP connectors are included with your AI Analyst at no extra cost.

What can my AI Analyst do with a connected tool today?

It can read and act. Read tools let it look up deals, tickets, campaigns and messages to explain why a metric moved, answer a question or run a Routine. Write tools let it take action in the tool, like updating a deal stage, sending a Slack message or creating a task. Every action follows the permissions you set, and new tools start on Needs approval.

Give your AI Analyst the full picture

Connect the tools where your business happens, official or custom, and let your AI Analyst explain what changed and why.