What is Infa
Infa Chrome Extension
How to use and install our Chrome Extension
Community
Browse community design systems
Release Notes
Featuring the latest changes to keep you up-to-date
Research Program
Participate in shaping the future of Infa
SOC 2 Type II Compliance Badge
Enterprise Ready
SOC 2 Type II certified for enterprise-level security and compliance
EventsLearnPricing
Sign up for free

Feedback

Share your feedback

Close
Anonymous submissions are auto-posted to #feedback channel. You can also share directly in Slack.

Need help?

Reach out to contact@infa.ai or see docs

Navigation
Search...
⌘ K
Focus sentinel
Close

Search Documentation

PressESCto close
Focus sentinel
Infa Documentation
  • General Information
    • Boards
    • Components
      • Main Components Vs Component Views
      • Component Tagging
      • Component Anatomy
    • Labels
    • Teams
    • Authentication
    • Permissions
      • Inviting People to Teams
      • Inviting People to Boards
    • Billing & Subscription
      • Managing Subscription
      • Promo Code Activation
    • Data Import, Export & Sync
      • Local vs. Cloud Boards
  • App Blocks
    • Building App Blocks
  • Chrome Extension
    • Deep Links
    • Using Labels
    • Updating the Extension
  • Integrations
    • MCP Server
    • Claude Code Plugin
    • External API
    • Progressive Web App
    • Figma Plugin
    • Coda Pack
    • Overview
    • Managing Runs
    • Board Agents
    • Overview
    • Infa Capture
    • Installation
    • Authentication
    • Connect a Board
    • Run Modes
    • Hooks & Agents
    • File Sync
    • CLI Reference
Switch to Light theme
Switch to Dark theme
TermsPrivacyChat with Us
  1. Docs
  2. Integrations

Infa Capture

A browser element selector that grabs a component's context and hands it to your clipboard, a comment, or AI.

Infa Capture is available on all Infa plans (Free, Pro, and Enterprise).

Infa Capture is a lightweight browser overlay that lets you point at any element in your running app, capture its context — page url, element xpath, component name, props, and source file — and send it where it needs to go. It is the same element selector the Infa CLI serves into your local preview, published as the standalone infa-capture package.

Copy link
Overview

We at Infa built Capture so the gap between "I see this component" and "I can act on it" disappears. You open the overlay, click an element, and pick what to do with it.

Evolve
Copy the selected element's context to your clipboard to paste into any AI tool
AI
Build a ready-to-send AI prompt from the context plus your question
Comment
Leave feedback anchored to the element — posted to your board or a Slack channel

Copy link
Opening the overlay

When the Infa CLI is running (infa preview), the overlay is injected into your app automatically. You trigger it with a keyboard shortcut:

  • macOS: Cmd+Shift+G
  • Windows and Linux: Ctrl+Shift+G

Hover to highlight an element, click to select it, then choose a mode in the panel.

Copy link
Modes

ModeWhat it doesNeeds an account
EvolveCopies a context block (url, xpath, component, props, source, code) to your clipboardNo
AIAssembles an AI prompt from the context and your question, then copies itNo
CommentSends feedback anchored to the element to your board, or to a Slack webhookComment-to-board only

Press Shift+Tab to cycle modes, or run the active mode with Cmd/Ctrl+Enter.

Copy link
Manage context

Every mode shows a "Manage context" card with a checkbox for each piece of captured data — the page url, the element xpath, the component, its source file, the file hierarchy, props, and code. You untick anything you do not want to share, so the payload carries exactly what you intend.

Copy link
AI mode

AI mode turns a selection into a prompt you can paste into Claude, Cursor, ChatGPT, or any MCP-aware client. By default the prompt points the receiving AI at the Infa MCP server so it can read your board directly.

info icon
Configurable prompt

Teams can replace the default with their own template — see Configuring the AI prompt below.

Copy link
Configuring the AI prompt

Set ai.prompt in your repo's .infa/config.yml. The template supports these placeholders, substituted when you copy:

PlaceholderReplaced with
{context}the selected element's context block
{question}what you typed in AI mode
{board_id}the connected board id
{paper_id}the current paper id
.infa/config.yml
Copy code
Copy code
ai:
prompt: |
You are helping with the ACME design system. Use our docs at https://acme.dev/docs.
{context}
Task:
{question}

If ai.prompt is not set, Capture uses a built-in default that installs and uses the Infa MCP server from https://infa.ai/docs/mcp.

Copy link
Using it without the CLI

Capture ships as an npm package you can host yourself:

npm install infa-capture

It exposes the built overlay (infa-capture/grab.js) plus a small helper to serve it. The host you serve it from provides the backend for the comment and AI actions, while the evolve and AI clipboard flows work entirely on the client.

Copy link
Related Topics

  • Infa CLI
  • Installation
  • MCP Server

Content Feedback

Feedback on selected content

Close
Anonymous submissions are auto-posted to #feedback channel. You can also share directly in Slack.

Need help?

Reach out to contact@infa.ai or see docs

PreviousOverview
NextInstallation