Skip to main content
Glama
whit3rabbit

Camoufox MCP Server

by whit3rabbit

browse_session_start

Start an isolated, short-lived browser session with anti-detection and configurable fingerprint spoofing for private browsing and automated web tasks.

Instructions

Start an isolated short-lived browser session.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
osNoOptional OS to spoof. Can be 'windows', 'macos', or 'linux'. If not specified, will rotate between all OS types.
argsNoAdditional browser command-line arguments to pass to the browser. Rejected unless CAMOUFOX_MCP_ALLOW_UNSAFE_OPTIONS=1; denied args are always rejected.
geoipNoAutomatically detect geolocation based on IP address.
proxyNoProxy configuration for routing browser traffic through an HTTP(S) proxy. Proxy servers are checked against the same local-network URL policy as page requests.
localeNoBrowser locale (e.g., 'en-US', 'fr-FR').
windowNoSet fixed window size [width, height] instead of random generation. An empty array [] is accepted and treated as if the window parameter was not specified.
timeoutNoTimeout in milliseconds for page load (5-300 seconds).
headlessNoRun browser in headless mode. Auto-detects best mode for environment if not specified.
humanizeNoEnable realistic cursor movements and human-like behavior for better stealth and anti-detection.
viewportNoCustom viewport dimensions.
block_webglNoBlock WebGL to prevent fingerprinting and tracking.
block_imagesNoBlock all images for faster loading, reduced bandwidth, and lightweight browsing.
block_webrtcNoBlock WebRTC entirely for enhanced privacy and stealth.
disable_coopNoDisable Cross-Origin-Opener-Policy for sites that require it.
enable_cacheNoCache pages, requests, etc. Uses more memory but improves performance when revisiting pages.
waitStrategyNoWait strategy for page load. Defaults to 'domcontentloaded'. 'load' waits for all resources, 'networkidle' waits for network activity to finish.domcontentloaded
captchaPolicyNoChallenge 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_addonsNoList of default addons to exclude (e.g., ['ublock_origin']). Rejected unless CAMOUFOX_MCP_ALLOW_UNSAFE_OPTIONS=1.
includeConsoleNoInclude bounded page console diagnostics in the JSON response.
includeNetworkNoInclude bounded network diagnostics in the JSON response.
stealthProfileNoConvenience profile for common Camoufox browser settings. Explicit options override profile values.normal
firefox_user_prefsNoCustom Firefox user preferences to set. Rejected unless CAMOUFOX_MCP_ALLOW_UNSAFE_OPTIONS=1; denied prefs are always rejected.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
browserYes
expiresAtYes
sessionIdYes
selectedOSYes
headlessModeYes
captchaPolicyYes
stealthProfileNo
Behavior3/5

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

Annotations already declare readOnlyHint=false and openWorldHint=true. The description adds the novel context that sessions are isolated and short-lived, which is useful. However, it doesn't disclose what 'start' returns or whether sessions require explicit closing, though the output schema covers some of that. Moderate added value beyond annotations.

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?

The description is a single six-word sentence with zero fluff, making it extremely conciseness and front-loaded. It earns its place but is perhaps too terse, missing the opportunity to add workflow context. Still, it is appropriately concise for a simple action.

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?

Despite having 22 parameters, an output schema, and nested objects, the description is extremely underspecified. It doesn't explain the session lifecycle, how this tool relates to sibling browse_session_* tools, or important defaults. The schema and output schema mitigate but don't eliminate the gap; the description fails to place the tool in the broader workflow.

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%, so all 22 parameters already have individual descriptions. The tool description adds no parameter semantics, and the baseline for high schema coverage is 3. It doesn't compensate or add any extra meaning beyond the schema.

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?

The description uses a specific verb ('start') and names the resource ('browser session'), adding scope with 'isolated short-lived.' This distinguishes it from sibling session tools that navigate or close sessions. However, it remains terse and doesn't elaborate on what a session entails, so it doesn't earn a 5.

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?

The description gives no guidance on when to use this tool versus alternatives like 'browse' or other browse_session_* tools. It doesn't state that this should be called before other session operations or when a one-off 'browse' is more appropriate. There's no mention of exclusions or alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/whit3rabbit/camoufox-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server