camoufox-agent

browse_inspect

Read-only

Inspect a single element to retrieve its box model, computed styles, matched CSS rules, attributes, visibility, overflow, and accessibility tree for debugging layout or styling issues.

Instructions

Inspect one element like DevTools: box model, computed styles, matched CSS rules, attributes, visibility, overflow, accessibility tree.

Input Schema

Name	Required	Description	Default
`os`	No	Optional OS to spoof. Can be 'windows', 'macos', or 'linux'. If not specified, will rotate between all OS types.
`url`	No	URL to inspect (one-shot). Provide exactly one of url or sessionId.
`args`	No	Additional browser command-line arguments to pass to the browser. Rejected unless CAMOUFOX_MCP_ALLOW_UNSAFE_OPTIONS=1; denied args are always rejected.
`frame`	No	CSS selector of an iframe. The action's selector is resolved inside this iframe.
`geoip`	No	Automatically detect geolocation based on IP address.
`proxy`	No	Proxy configuration for routing browser traffic through an HTTP(S) proxy. Proxy servers are checked against the same local-network URL policy as page requests.
`locale`	No	Browser locale (e.g., 'en-US', 'fr-FR').
`window`	No	Set fixed window size [width, height] instead of random generation. An empty array [] is accepted and treated as if the window parameter was not specified.
`timeout`	No	Timeout in milliseconds for page load (5-300 seconds).
`headless`	No	Run browser in headless mode. Auto-detects best mode for environment if not specified.
`humanize`	No	Enable realistic cursor movements and human-like behavior for better stealth and anti-detection.
`maxRules`	No	Max matched CSS rules to return.
`selector`	Yes	CSS selector of the element to inspect (first match).
`viewport`	No	Custom viewport dimensions.
`emulation`	No	Context emulation for diagnosing how the page behaves under other conditions.
`sessionId`	No	Existing session, inspected at its current page.
`properties`	No	Computed style properties to return. Defaults to a layout/typography set.
`block_webgl`	No	Block WebGL to prevent fingerprinting and tracking.
`block_images`	No	Block all images for faster loading, reduced bandwidth, and lightweight browsing.
`block_webrtc`	No	Block WebRTC entirely for enhanced privacy and stealth.
`disable_coop`	No	Disable Cross-Origin-Opener-Policy for sites that require it.
`enable_cache`	No	Cache pages, requests, etc. Uses more memory but improves performance when revisiting pages.
`waitStrategy`	No	Wait strategy for page load. Defaults to 'domcontentloaded'. 'load' waits for all resources, 'networkidle' waits for network activity to finish.	domcontentloaded
`captchaPolicy`	No	Challenge handling policy. 'detect' reports signals, 'pause' returns state for human action, 'fail' returns an error, 'attempt' returns enhanced challenge metadata, interactive elements, a bounded screenshot, and a suggested strategy. When CAPTCHA_AUTONOMOUS=true, responses are marked for LLM-assisted handling and include provider-specific challengePlaybook context when known.
`exclude_addons`	No	List of default addons to exclude (e.g., ['ublock_origin']). Rejected unless CAMOUFOX_MCP_ALLOW_UNSAFE_OPTIONS=1.
`includeConsole`	No	Include bounded page console diagnostics in the JSON response.
`includeNetwork`	No	Include bounded network diagnostics in the JSON response.
`stealthProfile`	No	Convenience profile for common Camoufox browser settings. Explicit options override profile values.	normal
`firefox_user_prefs`	No	Custom Firefox user preferences to set. Rejected unless CAMOUFOX_MCP_ALLOW_UNSAFE_OPTIONS=1; denied prefs are always rejected.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Oct 29, 2026

TDQS

A3.5/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, idempotentHint=false, so the safety profile is covered. The description adds the DevTools-equivalent mental model of what is inspected, but says nothing about the one-shot url vs existing sessionId modes, timeouts, or that a live page load occurs — the annotation bar is lower, so a 3 fits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with a tight enumeration and no filler. The DevTools analogy earns its place by compressing a lot of expectation into three words; the list is long but each item is a distinct output category.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 29 parameters, a full output schema, and 100% schema coverage, the description needs only to establish scope and return shape, which it does. The remaining gaps (url vs sessionId one-shot semantics, target page selection) are handled by the schema and annotations rather than the prose.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% across all 29 parameters, so the schema carries the semantics. The description only loosely maps to a few of them ('matched CSS rules' → maxRules, 'computed styles' → properties) and adds no syntax or format guidance beyond what the schema already states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('inspect') and resource ('one element') and enumerates exactly what comes back: box model, computed styles, matched CSS rules, attributes, visibility, overflow, accessibility tree. The 'one element' scoping implicitly separates it from page-level siblings like browse_snapshot or browse_outline, but no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the DevTools analogy and the 'one element' phrasing. There is no explicit when-to-use statement, no exclusion, and no pointer to browse_snapshot, browse_extract, or browse_find as the alternative for broader or different extraction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.