Documentation

Scout docs

Scout exposes capability-owned surfaces that agent clients can make available to the agent running inside them. Runtime surfaces like browser, canvas, extension, and payment live inside one browser runtime, while platform adapters pair through their own runtime.

Runtime surfaces & adaptersExtension-backed browser stateMCP auth or extension provider key

What it is

A browser automation environment for AI agents

Scout is a browser automation environment with capability-owned surfaces. Agent clients expose the selected surface's tools to the agent running inside the client.

Public runtime surfaces like browser, canvas, extension, and payment live inside one browser runtime, and platform adapters pair on their own boundary, so the agent only gets the capabilities the workflow actually needs.

The extension has its own app path and bundled tool surface; it is not configured as another public surface.

Each surface owns its capability boundary, endpoint, tool catalog, and runtime adapter.

The shared runtime handles auth, request identity, allowance resolution, and transport.

Setup paths

Agent clients or Chrome extension

Scout has two setup paths: agent clients connect to public surfaces for external workflows, and the extension app path for real-browser workflows.

IDE and CLI agents install or configure only the public surfaces their agent needs, then authenticate with OAuth or an access token.

The extension uses Scout's app flow and its own built-in tool surface for real-browser workflows.

Extension users provide an AI provider or gateway key in settings so Scout can route model requests.

How to start

Choose your path, then configure it

Start by choosing the path you are actually using. Agent clients need surface configuration and auth; the Chrome extension needs the app install and a provider key.

For Claude Code, IDE agents, or CLI harnesses, configure the browser runtime for browser, canvas, extension, or payment workflows, and add the Figma adapter only when design-file work is in scope.

For agent clients, use OAuth by default and create access tokens only for CI, scheduled jobs, and non-interactive clients.

For the Chrome extension, add the AI provider key from the model provider you want to use; do not copy runtime configs into the extension.

Verify agent connections with tool discovery before attempting longer automations.

Choose your browser path

Pick the browser context your workflow actually needs before you wire an MCP client.

Hosted browser connector

The default browser-automation path. Configure the browser MCP server in your client, authenticate, and let Scout run browser automation through that connector.

Browser state

Clean connector-managed browser sessions. No extension. No existing cookies or tabs unless the workflow attaches to a chosen browser target.

Best for

IDE agents that need a standard MCP server

CI, scheduled jobs, scraping, and isolated runs

Automation that should not inherit your personal browser state

Requirements

An MCP-compatible client

The public browser connector endpoint at https://mcp.scout.i.ng/browser

OAuth for normal use, or a Scout MCP token only when browser-based auth is impossible

Chrome extension app

The app path. The extension uses Scout's built-in runtime to operate your real browser with the AI provider key you supply.

Browser state

Your real Chrome session via the Scout extension and Scout's app-side runtime.

Best for

Workflows that require your real logged-in browser

Using existing tabs, sessions, cookies, and extension state

Operator-style tasks where the browser should remain visible and persistent

Requirements

The Scout Chrome extension

A connection to Scout's app runtime

An AI provider or gateway API key in extension settings

A workflow that explicitly benefits from existing authenticated browser state

Connector server setup

Configure the hosted browser connector, authenticate, then verify the tool catalog with a small real call.

Client

Cursor

Connect Cursor to Scout's hosted browser connector, complete browser-based OAuth, and verify the tool catalog before you start using Scout in chat.

Setup

Add the Scout browser connector entry to .cursor/mcp.json.

Save the file and let Cursor reload the MCP configuration.

Choose the Scout server when Cursor prompts to connect.

SnippetJSON

// Add to Cursor settings: .cursor/mcp.json
{
  "mcpServers": {
    "scout": {
      "type": "http",
      "url": "https://mcp.scout.i.ng/browser"
    }
  }
}

Authentication

Cursor should open the browser sign-in flow automatically on first connect. Complete the OAuth prompt, then return to Cursor and confirm the Scout server appears under MCP tools.

Verify

Open Cursor Settings > Tools & MCP and confirm the Scout server is connected.

Ask Cursor: "List the Scout MCP tools available in this workspace."

Run a low-risk verification task such as: "Use Scout MCP tools to open example.com and snapshot main."

Access tokens

Use Scout MCP tokens only for clients and jobs that cannot complete browser-based OAuth.

When to use MCP tokens

Use browser-based OAuth for normal interactive setup. Switch to access-token authentication only when your client cannot complete the sign-in flow or when you need non-interactive automation.

Steps

Prefer OAuth discovery for local development and everyday IDE use.

Use a Scout MCP token only for CI, scheduled jobs, or MCP clients without browser-based OAuth.

Keep the token scoped to the narrowest environment you can tolerate, ideally development or staging.

Revoke the token when the integration or job no longer needs it.

CI and headless automation

For CI or headless automation, attach a Scout MCP token as the Authorization header. This keeps the transport the same while bypassing browser-based login.

Steps

Generate a Scout MCP token from the Scout account UI or token management flow.

Store it in your CI secret store instead of committing it to the repo.

Inject it into the MCP client config as a Bearer header at runtime.

Rotate or revoke it after the automation job, especially for temporary workflows.

Programmatic MCP clients

Programmatic MCP callers can also use a Scout MCP token when they cannot complete OAuth. The auth shape is the same once the request reaches Scout: a userId plus derived workerId, with tokenId included for token-based access.

Steps

Use OAuth-derived MCP tokens when you can.

Fall back to a Scout MCP token only when browser sign-in is impossible.

Keep the token in environment variables or your secret manager.

Verify the connection with listTools() before starting a long-running job.

Environment variables

Optional configuration knobs for MCP clients, BYOK provider keys, and wallet-backed payments.

MCP Token

Optional

Fallback credential for CI or non-OAuth clients. Supply it as a Bearer header when your MCP client cannot complete the browser sign-in flow.

SnippetTEXT

smt_xxxxx.yyyyy

AI Provider Key (BYOK)

Optional

Your personal AI provider or gateway key for BYOK mode. Configure it in the extension settings so model usage is billed directly by the provider you choose.

SnippetTEXT

sk-...

Wallet Private Key

Optional

Supply it as the X-Wallet-Private-Key request header on the browser MCP server. Only the payment tools (balance, pay, transfer) read it for the current request; Scout never stores it. Chrome extension users set it in extension settings instead.

Wallet Network

Optional

Supply it as the X-Wallet-Network request header on the browser MCP server. Defaults to Base Sepolia (testnet). Set to base for mainnet wallet-backed assets.

Default: base-sepolia

Security recommendations

Keep capability, identity, and browser-state boundaries explicit.

Keep AI automation away from production by default

Do not default to production data when connecting an MCP client. Prefer development or staging environments, and keep real customer data away from exploratory AI workflows whenever possible.

Review tool calls, especially after reading untrusted content

Leave manual approval enabled in your MCP client and review tool calls before execution. Prompt injection remains a real risk whenever the model can read untrusted page content and then decide what to run next.

Use the right browser path for the risk level

Prefer hosted browser connector sessions for scraping, testing, and untrusted sites. Reserve the extension path for workflows where you explicitly want your real browser cookies, sessions, and authenticated state.

Treat MCP tokens like high-value secrets

Scout MCP tokens are powerful credentials. Store them in secret managers, scope them narrowly, rotate them when workflows change, and revoke them when an integration ends.

Constrain access rather than relying on the model to behave

Reduce the available action set when possible. Install or configure only the connector MCP servers needed for the workflow, and use the shortest-lived credential that still satisfies the automation.

Quickstart snippets

Small, copyable examples for the browser connector loop.

MCP token

SnippetJSON

{
  "mcpServers": {
    "scout": {
      "type": "http",
      "url": "https://mcp.scout.i.ng/browser",
      "headers": {
        "Authorization": "Bearer <mcp-token>"
      }
    }
  }
}

Programmatic client fallback

SnippetTYPESCRIPT

import { Client } from "@modelcontextprotocol/sdk/client";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js";

const transport = new StreamableHTTPClientTransport(
  new URL("https://mcp.scout.i.ng/browser"),
  {
    requestInit: {
      headers: {
        Authorization: "Bearer " + process.env.SCOUT_MCP_TOKEN,
      },
    },
  },
);

const client = new Client({ name: "batch-runner", version: "1.0.0" });
await client.connect(transport);

const { tools } = await client.listTools();
console.log(tools.map((tool) => tool.name));

const result = await client.callTool({
  name: "browser-launch",
  arguments: { url: "https://example.com" },
});

console.log(result);

Snapshot filtering guide

Trim the accessibility tree before extraction to cut tokens and keep the model focused.

Exclude Decorative Elements

Strip decorative elements (icons, separators, generic containers) that add tokens without useful information.

Impact

Varies by page — contributes to up to 75% combined reduction with other filters

SnippetTYPESCRIPT

browser-snapshot({ excludeDecorative: true })

Role-Based Filtering

Filter the accessibility tree by ARIA roles. Remove roles that aren't relevant to your task — for example, exclude 'img' and 'separator' when extracting text content.

Impact

20–40% reduction depending on page structure

SnippetTYPESCRIPT

browser-snapshot({ excludeRoles: ["img", "separator", "presentation"] })

Depth Limiting

Limit how deep the accessibility tree is traversed. Shallow depths (2–4) capture top-level navigation and headings. Deeper depths (6–8) capture interactive elements inside nested components.

Impact

Configurable — deeper pages benefit most

SnippetTYPESCRIPT

browser-snapshot({ maxDepth: 4 })

Element Scoping

Scope the snapshot to a specific element using a CSS selector. Only the subtree rooted at the matched element is included. Ideal when you know the content region (e.g., 'main', '#content', 'article').

Impact

50–75% reduction when scoping to content region

SnippetTYPESCRIPT

browser-snapshot({ selector: "main" })

Stacked Filtering

Combine multiple filters for maximum reduction. The recommended starting point for most extraction tasks: scope to main content, remove decorative nodes, and limit depth.

Impact

Up to 75% combined reduction

SnippetTYPESCRIPT

browser-snapshot({ selector: "main", excludeDecorative: true, maxDepth: 6 })

Recipes

Small, copyable end-to-end recipes for common extraction and automation tasks.

Extract Structured Data

Navigate to a page and extract content using DOM property extraction.

Steps

Navigate to the target URL

Snapshot the main content area with decorative filtering

Use browser-extract with property: 'article' for clean content or 'text' for element text

SnippetTYPESCRIPT

// 1. Navigate to the target page
await callTool("browser-navigate", {
  action: "goto",
  url: "https://example.com/products",
});

// 2. Take a filtered snapshot (main content only)
const snapshot = await callTool("browser-snapshot", {
  selector: "main",
  excludeDecorative: true,
});

// 3. Extract article content (clean markdown via Defuddle)
const article = await callTool("browser-extract", {
  property: "article",
});

// 4. Or extract specific element text
const heading = await callTool("browser-extract", {
  property: "text",
  selector: "h1",
});

Fill and Submit Forms

Fill form fields and submit using element refs from the accessibility snapshot.

Steps

Snapshot the page to discover form field refs

Fill each field using browser-interact with action: fill

Click the submit button

Re-snapshot to verify the result

SnippetTYPESCRIPT

// 1. Snapshot to find the form
const snapshot = await callTool("browser-snapshot");

// 2. Fill in the form fields using @e refs from the snapshot
await callTool("browser-interact", {
  action: "fill",
  elementRef: "@e12",        // email input
  text: "user@example.com",
});
await callTool("browser-interact", {
  action: "fill",
  elementRef: "@e14",        // password input
  text: "secure-password",
});

// 3. Click the submit button
await callTool("browser-interact", {
  action: "click",
  elementRef: "@e18",        // submit button
});

// 4. Wait for navigation and verify
const result = await callTool("browser-snapshot");

Batch Operations Pipeline

Chain navigate → snapshot → extract in a single batch call to minimize round-trips.

Steps

Define all operations as an array of { tool, params } objects

Send them all at once with browser-batch (max 10 actions)

Process the ordered batch.results array

SnippetTYPESCRIPT

// Use browser-batch to execute multiple operations in one round-trip
const batch = await callTool("browser-batch", {
  actions: [
    { tool: "browser-navigate", params: { action: "goto", url: "https://site-a.com" } },
    { tool: "browser-snapshot", params: { selector: "main", excludeDecorative: true } },
    { tool: "browser-extract", params: { property: "article" } },
  ],
});

// batch.results[0] → navigation confirmation
// batch.results[1] → filtered snapshot
// batch.results[2] → extracted content

Efficient Multi-Page Crawling

Block unnecessary resources and crawl multiple pages for bulk content extraction.

Steps

Set up route interception to block images, fonts, and CSS

Navigate to the starting page

Use browser-crawl with an extraction expression

SnippetTYPESCRIPT

// Block images and stylesheets to speed up page loads
await callTool("browser-route", {
  pattern: "**/*.{png,jpg,gif,svg,css,woff,woff2}",
  action: "abort",
});

// Navigate and extract — pages load faster without media
await callTool("browser-navigate", {
  action: "goto",
  url: "https://example.com/articles",
});

// Crawl with resource blocking built in
const results = await callTool("browser-crawl", {
  urls: ["https://example.com/articles"],
  enqueueStrategy: "same-hostname",
  maxRequestsPerCrawl: 50,
  blockedResources: ["image", "stylesheet", "font", "media"],
  expression: "document.querySelector('article')?.innerText",
});

Mobile Device Testing

Set viewport size, user agent, and network throttling to test responsive design and performance.

Steps

Resize viewport to mobile dimensions with browser-resize

Set user agent and locale with browser-emulate

Apply network throttling with custom throughput and latency values

Navigate and capture a full-page screenshot

Collect performance metrics

SnippetTYPESCRIPT

// 1. Set mobile viewport size
await callTool("browser-resize", {
  width: 390,
  height: 844,
});

// 2. Set mobile user agent and locale
await callTool("browser-emulate", {
  userAgent: "Mozilla/5.0 (iPhone; CPU iPhone OS 17_0 like Mac OS X) AppleWebKit/605.1.15",
  locale: "en-US",
  colorScheme: "light",
});

// 3. Simulate slow network conditions
await callTool("browser-throttle", {
  downloadThroughput: 50000,    // 50 KB/s (slow 3G)
  uploadThroughput: 25000,      // 25 KB/s
  latency: 2000,                // 2s RTT
});

// 4. Navigate and screenshot for visual comparison
await callTool("browser-navigate", { action: "goto", url: "https://example.com");
const screenshot = await callTool("browser-screenshot", {
  target: "page",
});

// 5. Check performance metrics
const metrics = await callTool("browser-metrics");
// → { domContentLoaded, domInteractive, firstContentfulPaint, firstPaint, loadComplete }

File & Clipboard Operations

Handle file downloads, attachments, and clipboard operations in automated workflows.

Steps

Use browser-download to wait for and capture downloads

Use browser-attach to attach files to <input type='file'> elements

Use browser-evaluate for clipboard access

SnippetTYPESCRIPT

// 1. Set up clipboard read access
await callTool("browser-evaluate", {
  expression: "await navigator.clipboard.readText()",
});

// 2. Click a download button and check downloads
await callTool("browser-interact", {
  action: "click",
  elementRef: "@e25",            // "Download PDF" button
});
const downloads = await callTool("browser-download", {
  action: "list",          // list all downloads
});

// 3. Attach a file to a file input
await callTool("browser-attach", {
  selector: "input[type=file]",
  files: ["/path/to/document.pdf"],
});

Connector reference

Verified against the registered connector handler surfaces so browser, canvas, extension, and payment appear as runtime surfaces and Figma as a platform adapter.

Figma

mcp.scout.i.ng/figma

Figma exposes a large MCP-first tool surface for document structure, component systems, styling, variables, export, and plugin-runtime workflows.

MCP-first71 commands

Open Figma page

Hover a command to preview what it does.

Content

Inspect and mutate nodes, components, layout, typography, fills, effects, geometry, and document structure.

figma-ancestors

figma-auto_layout

figma-blend

figma-boolean_op

figma-bounds

figma-children

figma-clone

figma-code_block

figma-component

figma-component_props

figma-constraints

figma-corners

figma-create

figma-css

figma-delete

figma-detach

figma-document

figma-effects

figma-fills

figma-find

figma-flatten

figma-font

figma-group

figma-image

figma-import_component

figma-import_style

figma-instance

figma-layout

figma-list_components

figma-list_fonts

figma-list_styles

figma-move

figma-node

figma-opacity

figma-paints

figma-reactions

figma-rename

figma-reparent

figma-resize

figma-strokes

figma-style

figma-swap_component

figma-text

figma-text_ranges

figma-transform

figma-typography

figma-ungroup

figma-update

figma-variant

figma-vector

Navigation

Move between pages, focus the viewport, and manage the active selection in a live document.

figma-create_page

figma-delete_page

figma-focus

figma-page

figma-pages

figma-select

figma-selection

figma-switch_page

figma-viewport

Management

Manage variable collections, variables, tokens, and dev-status metadata.

figma-create_variable

figma-create_variable_collection

figma-dev_status

figma-list_variable_collections

figma-list_variables

figma-token

figma-variable

Interaction

Use the plugin runtime for toasts and history control.

figma-notify

figma-undo

Storage

Read and write plugin-scoped storage surfaces.

figma-plugin_data

figma-shared_plugin_data

Media

Export nodes and assets from the current Figma document.

figma-export

Tool parameters reference

Every registered MCP tool with its parameters and return shape, grouped by capability. Expand a group to inspect individual tools.

Content

50 tools

Inspect and mutate nodes, components, layout, typography, fills, effects, geometry, and document structure.

figma-ancestorscontent

Read the ancestor chain for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Ancestor chain for the node

figma-auto_layoutcontent

Read auto-layout configuration for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Auto-layout configuration for the node

figma-blendcontent

Read blend mode and opacity for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Blend mode and opacity for the node

figma-boolean_opcontent

Combine multiple vector nodes with a boolean operation.

nodeIdsstring[]requiredIds of at least two nodes to combine.

operation'EXCLUDE' | 'INTERSECT' | 'SUBTRACT' | 'UNION'requiredBoolean operation to apply.

Returns: Resulting boolean group node

figma-boundscontent

Read absolute geometry bounds for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Absolute document-space bounds for the node

figma-childrencontent

Read direct children for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Direct children of the node

figma-clonecontent

Clone a Figma scene node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

offsetXnumberoptionalOptional x offset for the clone.

offsetYnumberoptionalOptional y offset for the clone.

Returns: Cloned node summary

figma-code_blockcontent

Read or update the content of a Figma code block.

nodeIdstringrequiredCode block node id.

codestringoptionalNew code content for the code block.

codeLanguagestringoptionalNew code language for the code block.

Returns: Code block content and language

figma-componentcontent

Read component metadata for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Component metadata for the node

figma-component_propscontent

Read component properties for a Figma instance or component.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Component property definitions

figma-constraintscontent

Read layout constraints for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Layout constraints for the node

figma-cornerscontent

Read corner radius data for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Corner radius data for the node

figma-createcontent

Create a Figma node on the current page.

parentIdstringrequiredNode id of the parent that should receive the new node.

typestringrequiredFigma node type to create.

propertiesRecord<string, unknown>optionalInitial property overrides for the newly created node.

Returns: Created node summary

figma-csscontent

Read CSS declarations for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: CSS property declarations for the node

figma-deletecontent

Delete a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Deletion confirmation

figma-detachcontent

Detach a Figma instance from its component.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Detached node summary

figma-documentcontent

Read the current Figma document summary.

Returns: Current Figma document summary

figma-effectscontent

Read visual effects for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Visual effects for the node

figma-fillscontent

Read fill paints for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Fill paints for the node

figma-findcontent

Find Figma nodes by type or name within a subtree.

nodeIdstringoptionalRoot node id to search within.

namestringoptionalOptional substring to match against node names.

typesstring[]optionalOptional node type filters.

limitnumberoptionalMaximum number of results to return.

Returns: Matching node summaries

figma-flattencontent

Flatten one or more Figma nodes into a vector.

nodeIdsstring[]requiredOne or more Figma node ids to operate on.

Returns: Flattened vector node summary

figma-fontcontent

Read font information for a Figma text node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Font information for the node

figma-groupcontent

Group multiple Figma nodes.

nodeIdsstring[]requiredOne or more Figma node ids to operate on.

Returns: Created group node summary

figma-imagecontent

Read image paint summaries for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Image paint summaries for the node

figma-import_componentcontent

Import a published library component into the current document by key.

keystringrequiredPublished component key from the Figma library.

Returns: Imported component summary

figma-import_stylecontent

Import a published library style into the current document by key.

keystringrequiredPublished style key from the Figma library.

Returns: Imported style summary

figma-instancecontent

Read instance metadata for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Instance metadata for the node

figma-layoutcontent

Read layout properties for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Layout properties for the node

figma-list_componentscontent

List components in the current Figma document.

Returns: Components defined in the current document

figma-list_fontscontent

List all fonts available in the connected Figma runtime.

Returns: Available fonts

figma-list_stylescontent

List styles in the current Figma document.

styleType'EFFECT' | 'GRID' | 'PAINT' | 'TEXT'optionalOptional style type filter.

Returns: Local styles defined in the document

figma-movecontent

Move a Figma node.

nodeIdstringrequiredId of the node to move.

xnumberrequiredNew x position.

ynumberrequiredNew y position.

Returns: Moved node summary with new position

figma-nodecontent

Read identity and metadata for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Node identity and metadata

figma-opacitycontent

Read opacity information for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Opacity for the node

figma-paintscontent

Read fill and stroke paint summaries for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Fill and stroke paint summaries for the node

figma-reactionscontent

Read prototype reactions for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Prototype reactions for the node

figma-renamecontent

Rename a Figma node.

nodeIdstringrequiredId of the node to rename.

namestringrequiredNew name for the node.

Returns: Renamed node summary

figma-reparentcontent

Move a Figma node under a different parent.

nodeIdstringrequiredId of the node to move.

parentIdstringrequiredId of the new parent node.

indexnumberoptionalOptional insertion index within the new parent.

Returns: Reparented node summary

figma-resizecontent

Resize a Figma node.

nodeIdstringrequiredId of the node to resize.

widthnumberrequiredNew width in pixels.

heightnumberrequiredNew height in pixels.

Returns: Resized node summary

figma-strokescontent

Read stroke paints for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Stroke paints for the node

figma-stylecontent

Read style metadata for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Style metadata for the node

figma-swap_componentcontent

Swap a Figma instance to a different component.

nodeIdstringrequiredId of the instance node to swap.

componentIdstringrequiredId of the replacement component node.

Returns: Swapped instance summary

figma-textcontent

Read text properties for a Figma text node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Text properties for the node

figma-text_rangescontent

Read styled text ranges for a Figma text node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Styled character ranges for the node

figma-transformcontent

Read transform data for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Transform data for the node

figma-typographycontent

Read typography settings for a Figma text node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Typography settings for the node

figma-ungroupcontent

Ungroup a Figma group.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Ungrouped node summary

figma-updatecontent

Update properties on a Figma node.

nodeIdstringrequiredFigma node id to update.

propertiesRecord<string, unknown>requiredProperty key-value pairs to apply to the node.

Returns: Updated node summary

figma-variantcontent

Read variant information for a Figma component set.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Variant information for the node

figma-vectorcontent

Read vector paths and network details for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Vector paths and network details for the node

Navigation

9 tools

Move between pages, focus the viewport, and manage the active selection in a live document.

figma-create_pagenavigation

Create a new Figma page.

namestringrequiredName for the new page.

Returns: Created page summary

figma-delete_pagenavigation

Delete a Figma page.

pageIdstringrequiredId of the page to delete.

Returns: Deletion confirmation

figma-focusnavigation

Center the Figma viewport on a node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Viewport centered on the node

figma-pagenavigation

Read the active Figma page summary.

Returns: Active page summary

figma-pagesnavigation

List pages in the current Figma document.

Returns: Pages in the current document

figma-selectnavigation

Select one or more Figma nodes.

nodeIdsstring[]requiredOne or more Figma node ids to operate on.

Returns: Updated selection

figma-selectionnavigation

Read the current Figma selection summary.

Returns: Current page selection summary

figma-switch_pagenavigation

Switch the active Figma page.

pageIdstringrequiredId of the page to switch to.

Returns: Switched page summary

figma-viewportnavigation

Read the current Figma viewport state.

Returns: Current viewport state

Management

7 tools

Manage variable collections, variables, tokens, and dev-status metadata.

figma-create_variablemanagement

Create a new Figma variable.

collectionIdstringrequiredVariable collection id.

namestringrequiredName for the new variable.

resolvedType'BOOLEAN' | 'COLOR' | 'FLOAT' | 'STRING'requiredResolved type of the variable.

valueunknownoptionalInitial variable value.

Returns: Created variable summary

figma-create_variable_collectionmanagement

Create a new Figma variable collection.

namestringrequiredName for the new variable collection.

Returns: Created variable collection summary

figma-dev_statusmanagement

Read or update the dev status for a Figma node.

nodeIdstringrequiredId of the scene node.

statusstring | nulloptionalDev status value or null to clear.

Returns: Current dev status for the node

figma-list_variable_collectionsmanagement

List variable collections in the current Figma document.

Returns: Variable collections in the document

figma-list_variablesmanagement

List variables in the current Figma document.

Returns: Variables in the document

figma-tokenmanagement

Read token usage for a Figma node.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Design token bindings for the node

figma-variablemanagement

Read details for a Figma variable.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

Returns: Variable details

Interaction

2 tools

Use the plugin runtime for toasts and history control.

figma-notifyinteraction

Show a notification inside Figma.

messagestringrequiredNotification message to display in Figma.

timeoutnumberoptionalOptional duration in milliseconds.

Returns: Whether the notification was sent

figma-undointeraction

Trigger an undo in Figma.

Returns: Undo confirmation

Storage

2 tools

Read and write plugin-scoped storage surfaces.

figma-plugin_datastorage

Read or write plugin data on a Figma node or page.

keystringrequiredPlugin data key.

nodeIdstringoptionalOptional node id to read or write plugin data on.

valuestringoptionalOptional plugin data value to set.

Returns: Stored plugin data value

figma-shared_plugin_datastorage

Read, write, or enumerate shared plugin data stored at the document level. Shared plugin data is accessible by any Figma plugin.

namespacestringrequiredShared plugin data namespace. Any Figma plugin can read and write data under any namespace.

keystringoptionalData key within the namespace. Omit to list all keys stored under the namespace.

valuestringoptionalValue to write under the given key. When present alongside a key, the value is written before the result is returned.

Returns: Stored value or the keys in the namespace

Media

1 tools

Export nodes and assets from the current Figma document.

figma-exportmedia

Export a Figma node as an image or PDF.

nodeIdstringrequiredFigma node id to inspect within the connected Figma runtime.

format'JPG' | 'PDF' | 'PNG' | 'SVG'optionalExport format. Defaults to PNG.

scalenumberoptionalExport scale factor. Defaults to 1.

Returns: Base64-encoded exported asset bytes and metadata

Architecture notes

The small set of system concepts that actually change how you choose a path, authenticate, and operate Scout safely.

Connectors are configured separately so each workflow only exposes the capabilities it actually needs.

The extension follows Scout's app-side tool flow rather than appearing as another public connector users install directly.

Use the extension path only when the task depends on your real tabs, cookies, or authenticated browser state; otherwise keep the workflow on isolated connector sessions.

FAQ

Common questions about setup, authentication, browser state, security, and billing.

Scout docs

A browser automation environment for AI agents

Agent clients or Chrome extension

Choose your path, then configure it

Choose your browser path

Hosted browser connector

Chrome extension app

Connector server setup

Cursor

Access tokens

When to use MCP tokens

CI and headless automation

Programmatic MCP clients

Environment variables

MCP Token

AI Provider Key (BYOK)

Wallet Private Key

Wallet Network

Security recommendations

Keep AI automation away from production by default

Review tool calls, especially after reading untrusted content

Use the right browser path for the risk level

Treat MCP tokens like high-value secrets

Constrain access rather than relying on the model to behave

Quickstart snippets

MCP token

Programmatic client fallback

Snapshot filtering guide

Exclude Decorative Elements

Role-Based Filtering

Depth Limiting

Element Scoping

Stacked Filtering

Recipes

Extract Structured Data

Fill and Submit Forms

Batch Operations Pipeline

Efficient Multi-Page Crawling

Mobile Device Testing

File & Clipboard Operations

Connector reference

Figma

Content

Navigation

Management

Interaction

Storage

Media

Tool parameters reference

Content

Navigation

Management

Interaction

Storage

Media

Architecture notes

Clients choose connectors, workflows stay scoped

Authentication stays simple

Refs and coordination reduce brittleness

Limits and safety are intentional

FAQ