camoufox-mcp-python
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| os | No | Target OS fingerprint(s), comma-separated (windows, macos, linux) | |
| caps | No | Comma-separated capability groups (e.g., dangerous) | |
| debug | No | Print the config being sent to Camoufox (true/false) | false |
| geoip | No | Auto-match locale/timezone to proxy IP, or specify a target IP | |
| proxy | No | Proxy server URL (supports user:pass@host:port) | |
| addons | No | Comma-separated paths to extracted Firefox addons | |
| config | No | Camoufox fingerprint properties as a JSON string | |
| locale | No | Browser locale(s), comma-separated (e.g., en-US) | |
| window | No | Outer window size (e.g., 1280x720) | |
| headless | No | Run browser headlessly (true/false) | true |
| humanize | No | Cursor humanization (true, false, or number for max duration in seconds) | true |
| block_webgl | No | Disable WebGL (true/false) | false |
| block_images | No | Block image requests (true/false) | false |
| block_webrtc | No | Block WebRTC to prevent IP leaks (true/false) | true |
| disable_coop | No | Disable COOP for cross-origin iframe interactions (true/false) | false |
| enable_cache | No | Enable page/request caching (true/false) | false |
| webgl_config | No | WebGL vendor/renderer pair (e.g., 'Intel Inc.,Intel(R) UHD Graphics 620') | |
| user_data_dir | No | Path to persistent profile directory | |
| exclude_addons | No | Comma-separated default addon names to exclude (e.g., UBO) | |
| firefox_user_prefs | No | Firefox user preferences as a JSON string | |
| i_know_what_im_doing | No | Silence Camoufox warnings (true/false) | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_snapshotC | Capture the current accessibility snapshot. |
| browser_clickC | Perform click on a web page. |
| browser_hoverC | Hover over a web page element. |
| browser_dragD | Drag from one ref to another. |
| browser_select_optionC | Select one or more values in a dropdown. |
| browser_navigateC | Navigate to a URL. |
| browser_navigate_backA | Go back to the previous page. |
| browser_tabsC | List, create, close, or select a browser tab. |
| browser_typeC | Type text into an editable element. |
| browser_press_keyC | Press a key on the keyboard. |
| browser_fill_formB | Fill multiple form fields in one call. |
| browser_closeA | Close the current browser session. |
| browser_resizeB | Resize the current page viewport. |
| browser_wait_forB | Wait for text to appear or disappear, or for a fixed duration. |
| browser_take_screenshotB | Take a screenshot of the viewport, full page, or a referenced element. |
| browser_console_messagesC | Return collected console messages. |
| browser_network_requestsB | List network requests seen by the page. |
| browser_file_uploadD | Handle an active file chooser. |
| browser_handle_dialogC | Accept or dismiss an active dialog. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 19 tools
Each tool targets a distinct interaction or observation (e.g., click vs. hover vs. drag, type vs. press_key vs. fill_form). The only mild overlap is between type and fill_form, but their descriptions clearly scope them to single-element vs. multi-field actions. Overall, no two tools are easily confused.
All tools share the 'browser_' prefix, creating a strong family resemblance. However, the suffix pattern is mixed: some are verb-first (browser_click, browser_navigate) while others are resource-first (browser_tabs, browser_console_messages, browser_network_requests). Despite this, the prefix and clear action descriptions make the naming predictable.
At 19 tools, the set is slightly above the typical 3-15 range but well-justified for a comprehensive browser automation server. The count covers navigation, input, observation, and tab/window management without feeling redundant. A few tools could theoretically be combined (e.g., screenshot modes), but the granularity is reasonable.
The tool surface covers the core browser automation lifecycle: navigation (navigate, back), interaction (click, hover, drag, select, type, press_key, fill_form), waiting (wait_for), and introspection (snapshot, console, network, screenshot). It also handles dialogs, file uploads, tabs, resize, and closing, leaving no obvious dead ends for standard automation scenarios. Advanced features like JS evaluation are absent but not essential for basic browser control.