# Scout (oci · ghcr.io/klarlabs-studio/scout:1.15.3)
Browser automation MCP server with 84 tools. Pure CDP, DOM diffing, vision hybrid.
- Trust score: 42/100 (low)
- Change this week: −2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03
## Components
- oci · `ghcr.io/klarlabs-studio/scout:1.15.3`: 42/100 (this document), [markdown](https://verifymcp.io/servers/klarlabs-studio-scout/ghcr-io-klarlabs-studio-scout-1-15-3.md), [page](https://verifymcp.io/servers/klarlabs-studio-scout/ghcr-io-klarlabs-studio-scout-1-15-3)
## Channel facts
- Registry: `oci`
- Package: `ghcr.io/klarlabs-studio/scout:1.15.3`
- Transport: `stdio`
## Trust breakdown
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)
Scored 2026-08-03.
- **Supply Chain Security**: 0/100
- Malware scan not yet available for this package.
- CVE data not yet available for this package.
- Install-script risk not yet assessed.
- Dependency-health data not yet available.
- **Provenance & Transparency**: 45/100
- Source repository is publicly reachable at the declared URL.
- Provenance check failed: no build-provenance attestation is published.
- Clear OSI-approved license (MIT).
- Actively maintained (last published 7 days ago).
- Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 75/100
- AI-judged instruction clarity (good).
- Tool/resource definitions use about 5808 tokens (~66/item across 88 items; 88 tools + 0 resources), lean.
- Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
- Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).
- 94% of tool parameters carry a description.
- Structured output schemas are declared (16% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
- Implements a current MCP spec version (2026-07-28).
**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
## Install
### Claude
```bash
claude mcp add klarlabs-studio-scout -- docker run --rm -i ghcr.io/klarlabs-studio/scout:1.15.3
```
### Codex
```bash
codex mcp add klarlabs-studio-scout -- docker run --rm -i ghcr.io/klarlabs-studio/scout:1.15.3
```
### opencode
```json
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"klarlabs-studio-scout": {
"type": "local",
"command": [
"docker",
"run",
"--rm",
"-i",
"ghcr.io/klarlabs-studio/scout:1.15.3"
],
"enabled": true
}
}
}
```
### Hermes
```yaml
mcp_servers:
klarlabs-studio-scout:
command: "docker"
args: ["run", "--rm", "-i", "ghcr.io/klarlabs-studio/scout:1.15.3"]
```
### Other
```json
{
"mcpServers": {
"klarlabs-studio-scout": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/klarlabs-studio/scout:1.15.3"
]
}
}
}
```
## Changelog
Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.
### 2026-08-03 (score 42, +3)
- [functional improvement] Stability: unverified → 0.23
- [functional] MCP protocol: Implements a current MCP spec version (2026-07-28).
### 2026-08-01 (score 39, −5)
- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server
### 2026-07-27 (score 44, +33)
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Tool coverage: 16
- [functional] First check of Schema quality: good
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 94
### 2026-07-26 (score 11)
First indexed and scored.
- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server
## MCP tools (88)
### `accessibility_tree` (~32 tokens)
Get a compact accessibility tree showing all interactive elements.
Input parameters:
- `url` (string): Optional URL to navigate to before observing
### `annotated_screenshot` (~136 tokens)
Label all interactive elements with numbers and return their selectors/info. By default returns only the element list (compact). Set include_image=true to also get the screenshot with labels drawn on it. NOTE: label numbers are per-call only — after any DOM mutation (re-render, modal open, route change), the same label may point to a different element. Pair click_label with the most recent annotated_screenshot in the same turn; for stable identity across mutations use the returned selector.
Input parameters:
- `include_image` (boolean): Include base64 image data in response. Default false to avoid large responses. Use screenshot tool separately if you need the image.
### `app_state` (~50 tokens)
Extract global app state (Redux, Next.js, Nuxt, Remix, SvelteKit, Gatsby, Astro, Alpine, HTMX).
Input parameters:
- `url` (string): Optional URL to navigate to before observing
### `aria_violations` (~67 tokens)
Minimal accessibility scan grouped by impact (critical/serious/moderate/minor). Covers image-alt, button-name, link-name, label, duplicate-id, html-has-lang, landmark-one-main. Zero dependency — for full WCAG coverage run axe-core in your test pipeline.
Output parameters:
- `count` (integer)
- `critical` (array)
- `minor` (array)
- `moderate` (array)
- `serious` (array)
### `assert_text_contains` (~114 tokens)
Check that the given text appears on the page in one round-trip. If selector is set, searches only that element's text; otherwise searches body innerText. Returns ok=true with a surrounding snippet on hit, ok=false with a short page-tail snippet on miss. Replaces extract+string-match for post-action verification.
Input parameters:
- `case_insensitive` (boolean): Fold case when comparing. Default false.
- `selector` (string): Optional CSS selector to scope the search.
- `text` (string, required): Text to search for.
### `auto_extract` (~46 tokens)
Auto-detect repeating patterns (product cards, search results, list items) and extract structured data. No selectors needed.
Input parameters:
- `url` (string): Optional URL to navigate to before observing
### `back` (~31 tokens)
Navigate to the previous page in browser history (like clicking the browser Back button). Errors if there is no previous entry.
### `batch` (~88 tokens)
Execute multiple actions in a single call. Avoids repeated round-trips. Actions: click, type, fill_form_semantic, wait, scroll_to, click_label. Continues on error.
Input parameters:
- `actions` (array, required): Array of actions to execute. Each has action (click/type/fill_form_semantic/wait/scroll_to/click_label) plus selector/value/label/fields as needed.
### `check_readiness` (~58 tokens)
Check how ready the page is for interaction. Returns a 0-100 score, pending XHR count, skeleton/spinner presence, and suggestions for what to wait for.
Input parameters:
- `url` (string): Optional URL to navigate to before observing
Output parameters:
- `has_skeleton` (boolean)
- `has_spinner` (boolean)
- `pending_images` (integer)
- `pending_xhr` (integer)
- `score` (integer)
- `state` (string)
- `suggestions` (array)
### `click` (~50 tokens)
Click an element by CSS selector. Set wait=true for navigation clicks.
Input parameters:
- `selector` (string, required): CSS selector of element to click
- `wait` (boolean): If true wait for full page navigation after click
### `click_handle` (~107 tokens)
Click the element identified by a stable node_handle from a previous annotated_screenshot. Unlike click_label, the handle survives DOM mutations that would shuffle label numbers. Returns a stale_handle error when the element is no longer in the DOM — re-annotate and retry.
Input parameters:
- `handle` (string, required): Stable node handle from a previous annotated_screenshot call (the node_handle field). Survives DOM mutations that would shuffle label numbers; returns a stale_handle error if the element has since be…
### `click_label` (~38 tokens)
Click an element by its label number from annotated_screenshot.
Input parameters:
- `label` (string, required): Label number from annotated screenshot (e.g. 8)
### `click_text` (~103 tokens)
Click an element by its visible text. Resolution: aria-label exact match, then button/link text match, then closest interactive ancestor of a matching text node. Pass role="button"|"link" to disambiguate when text appears in both. Cheaper than annotated_screenshot for the common 'click that thing I can see' case.
Input parameters:
- `role` (string): Optional role filter: button or link.
- `text` (string, required): Visible text to match (exact
### `close_tab` (~49 tokens)
Close a named tab. Cannot close the currently active tab.
Input parameters:
- `name` (string): Tab name (for open_tab and switch_tab)
- `url` (string): URL to open in new tab
### `compare_tabs` (~51 tokens)
Compare content between two named tabs. Returns what's different, what's only in one tab.
Input parameters:
- `tab1` (string, required): Name of the first tab
- `tab2` (string, required): Name of the second tab
### `component_state` (~44 tokens)
Extract component state/props from any framework (React, Vue, Svelte, Angular, Alpine, Lit).
Input parameters:
- `selector` (string, required): CSS selector of the component root element
### `configure` (~179 tokens)
Change browser settings without restarting. Use headless=false to see the browser window. Set allow_private_ips=true for local-dev workflows (localhost, 127.0.0.1, private IPs). Pass fresh=true to force-kill the current page and start clean (use after observing session_dead in status).
Input parameters:
- `allow_private_ips` (boolean): Allow navigation to loopback (127.0.0.1
- `fresh` (boolean): Kill the current page and browser and start a fresh session even if headless/allow_private_ips didn't change. Use after observing session_dead=true in status or when accumulated SPA state needs to be…
- `headless` (boolean): Run browser in headless mode (no visible window). Omit to keep the current setting (default true); a missing value no longer silently switches to a visible window.
### `console_errors` (~64 tokens)
Get captured console.error / console.warn messages plus recent network 4xx/5xx failures. Auto-installs lightweight network observers, so failures recorded after the first call surface here without an explicit enable_network_capture.
Input parameters:
- `url` (string): Optional URL to navigate to before observing
Output parameters:
- `messages` (array)
- `network_failures` (array)
### `cookies_clear` (~104 tokens)
Clear cookies. With no name, drops all cookies via Network.clearBrowserCookies. With a name, deletes only that cookie (optionally scoped by domain/path). Use this when a backend has been restarted and the previous session token is invalid.
Input parameters:
- `domain` (string): Optional domain scope when deleting a single cookie.
- `name` (string): Cookie name to delete. Leave empty to clear all cookies.
- `path` (string): Optional path scope when deleting a single cookie.
### `cookies_list` (~51 tokens)
List all cookies for the active page (names + flags only — values are redacted). Useful for diagnosing stale-session issues after a backend restart.
Input parameters:
- `url` (string): Optional URL to navigate to before observing
Output parameters:
- `items` (array)
- `total` (integer)
### `cookies_set` (~83 tokens)
Set a cookie on the active page. Useful for restoring sessions or seeding state.
Input parameters:
- `domain` (string)
- `expires` (number)
- `http_only` (boolean)
- `name` (string)
- `path` (string)
- `same_site` (string)
- `secure` (boolean)
- `value` (string)
### `detect_auth_wall` (~46 tokens)
Check if the page is a login wall, paywall, or CAPTCHA. Returns type, confidence, and reason.
Input parameters:
- `url` (string): Optional URL to navigate to before observing
### `detect_dialog` (~48 tokens)
Check if a modal, dialog, popup, or overlay is currently visible. Returns its title, text, buttons, and inputs.
Input parameters:
- `url` (string): Optional URL to navigate to before observing
### `detect_frameworks` (~33 tokens)
Detect which frontend frameworks are active on the page.
Input parameters:
- `url` (string): Optional URL to navigate to before observing
### `discover_form` (~38 tokens)
Discover form fields with their labels, types, and CSS selectors.
Input parameters:
- `selector` (string): CSS selector for specific form (empty = all forms)
Output parameters:
- `action` (string)
- `fields` (array)
- `form_selector` (string)
- `method` (string)
### `dismiss_cookies` (~55 tokens)
Auto-dismiss cookie consent banners. Tries common selectors and text patterns (Accept, Agree, Got it, OK). Returns whether a banner was found and dismissed.
Input parameters:
- `url` (string): Optional URL to navigate to before observing
### `dispatch_event` (~139 tokens)
Dispatch a DOM event on an element. Useful for triggering SPA event handlers. Special cases: event_type='submit' on a