camoufox-agent

browse

Read-only

Navigate once to a URL and return bounded page content for checking, searching, or scraping websites.

Instructions

Navigate once and return bounded page content.

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`	Yes	The URL to navigate to and retrieve content from. Use this tool when users ask to visit, check, search, navigate, browse, fetch, or scrape websites. Must be a fully qualified URL (e.g., 'https://example.com').
`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.
`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.
`maxChars`	No	Maximum text or HTML characters to return.
`selector`	No	Optional CSS selector to limit extraction to one matching element.
`viewport`	No	Custom viewport dimensions.
`emulation`	No	Context emulation for diagnosing how the page behaves under other conditions.
`outputMode`	No	Response content mode. Defaults to visible text. Use 'html' only when raw HTML is explicitly needed.	text
`screenshot`	No	Capture a screenshot/image of the page after loading.
`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
`screenshotOptions`	No	Optional screenshot capture settings. Used only when screenshot is true.
`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
`url`	Yes
`html`	No
`text`	No
`title`	No
`status`	No
`message`	No
`maxChars`	Yes
`selector`	No
`truncated`	Yes
`outputMode`	Yes
`screenshot`	No
`contentType`	No
`diagnostics`	No
`challengeType`	No
`selectorFound`	No
`captchaIframes`	No
`captchaDetected`	No
`challengeSignals`	No
`challengeHandling`	No
`challengePlaybook`	No
`challengeProvider`	No
`suggestedStrategy`	No
`requiresUserAction`	No
`interactiveElements`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Oct 29, 2026

TDQS

C2.6/5.0

Behavior2/5

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

Annotations already declare readOnlyHint, destructiveHint=false, openWorldHint, and idempotentHint=false, so the safety profile is covered. The description adds only the word 'bounded', which gestures at maxChars truncation but does not explain it, nor does it mention timeout behavior, CAPTCHA handling, or that navigation is non-idempotent and may return different content each call.

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 no filler or repetition, which is structurally clean. It is arguably too terse for a 29-parameter tool, but that is an underspecification problem scored elsewhere, not a conciseness failure.

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

Completeness2/5

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

All output detail is legitimately offloaded to the output schema, but this tool has 29 parameters, nested objects, session siblings, and stealth/fingerprinting behavior with no explanation of defaults, tradeoffs, or when to reach for the session variants. One sentence is not complete enough for a tool of this complexity, even with a rich schema.

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, including enums, defaults, and constraints, so the schema does the heavy lifting. Per the baseline rule this scores 3; the description adds no parameter semantics beyond the single word 'bounded' pointing at maxChars, and nothing about the required url beyond what the schema states.

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

Purpose3/5

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

The verb 'navigate' and object 'page content' are specific enough to identify a one-shot fetch-and-return tool, and 'once' hints at the contrast with session-based siblings. However, it never names what distinguishes it from browse_session_navigate, browse_extract, or browse_snapshot, so an agent must infer positioning from the sibling list alone.

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

Usage Guidelines2/5

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

No when-to-use, when-not-to-use, or alternative tool is mentioned in the description. The 'once' wording weakly implies 'use this for a single page instead of a persistent session', but that is inference, not guidance. The fact that the schema's url field carries the actual use-case routing text means the description itself abdicates this dimension.

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