camoufox-agent

by Jul879n

Overview Schema Source Related Servers Discussions Admin

TypeScript

Hybrid

browse_sequence

Navigate to a URL once, run a bounded sequence of selector-based actions, then return the final page state.

Instructions

Navigate once, run bounded selector actions, then return final state.

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. Must be a fully qualified http or https URL.
`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.
`actions`	Yes	Bounded action sequence to run after navigation.
`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 final text, HTML, snapshot, or evaluate-result characters to return.
`selector`	No	Optional CSS selector to limit final content 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	Final response content mode.	text
`screenshot`	No	Capture a screenshot/image after all actions finish.
`block_webgl`	No	Block WebGL to prevent fingerprinting and tracking.
`maxElements`	No	Maximum final snapshot elements to return.
`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
`actions`	Yes
`message`	No
`maxChars`	Yes
`selector`	No
`snapshot`	No
`truncated`	Yes
`outputMode`	Yes
`screenshot`	No
`contentType`	No
`diagnostics`	No
`challengeType`	No
`initialStatus`	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

B3.1/5.0

Behavior3/5

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

Annotations already declare openWorld, non-idempotent, non-read-only, non-destructive, so the safety profile is covered. The description adds only the word 'bounded' as a hint at the 100-action cap. It says nothing about the single-use vs resumable session lifetime, side effects of click/fill/upload/download actions, or the human-in-the-loop and secret-handling capabilities that materially change how an agent should plan a 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; the sequence ordering is put first. Its brevity is close to excessive given the tool's surface area, but no sentence is wasted.

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?

For a tool with 31 parameters, deeply nested action variants, enums, an output schema, and a dense sibling set, one sentence leaves the critical decision information unstated: why this over 'browse' or 'browse_session_navigate', whether the session persists, and how failures mid-sequence are handled. Output shape is covered by the output schema, so that omission is acceptable; the rest is not.

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 31 parameters, including per-property docs for the oneOf action variants, so the schema carries the burden. The description adds no meaning beyond what is already documented, which is the baseline 3 case.

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 recognisable three-phase behavior (navigate once, run bounded selector actions, return final state), which is more than a restatement of the name. However, it never distinguishes this from siblings like 'browse', 'browse_session_navigate', or 'browse_session_action', so an agent cannot tell which one to reach for.

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?

There is no when-to-use, when-not-to-use, or alternative named anywhere in the description, despite a crowded sibling set. The single implied hint ('navigate once') weakly suggests a one-shot session, but nothing is stated explicitly.

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