Argus
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Capabilities
Features and capabilities supported by this server
| 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 |
|---|---|
| start_sessionA | Start a browser testing session and navigate to the given URL. Args: url: The URL to test (e.g. http://localhost:3000) headless: Run browser without visible window (default True) viewport_width: Browser viewport width in pixels viewport_height: Browser viewport height in pixels |
| get_page_stateA | Get the current page URL, title, and all interactive elements. Returns a numbered list of elements you can interact with using click(index), type_text(index, text), or select_option(index, value). |
| clickA | Click an interactive element by its index number from get_page_state(). Args: element_index: The [N] index of the element to click |
| type_textA | Type text into an input element. Args: element_index: The [N] index of the input element text: The text to type |
| select_optionB | Select an option from a dropdown/select element. Args: element_index: The [N] index of the select element value: The value or visible text to select |
| navigateB | Navigate to a specific URL. Args: url: The URL to navigate to |
| go_backB | Go back to the previous page. |
| scroll_downB | Scroll the page down to reveal more content. |
| screenshotB | Take a screenshot of the current page. Args: name: Name for the screenshot file (without extension) |
| get_errorsA | Get all console errors and network failures captured since the last check. Returns any JavaScript errors, unhandled exceptions, and HTTP 4xx/5xx responses detected during interaction. These are automatically recorded as bugs in the session report. |
| verify_actionA | Verify that a destructive action actually persisted by navigating to a page and checking. Call this AFTER performing a delete, edit, or toggle and seeing a success message. Navigates to verify_url (or the current page via GET) and checks whether the expected change is reflected in the page content. Args: action_type: One of "delete", "edit", or "toggle" target_text: For delete: the text of the deleted item. For edit: the NEW value you entered. verify_url: URL to navigate to for verification (e.g. the list page or edit page). If empty, navigates to the current URL via GET. |
| check_linksA | Crawl all internal links on the current page and check for dead links (404/5xx). Sends HEAD requests to each internal link found on the page. This can take several seconds on pages with many links. |
| check_performanceA | Measure page performance: load time, resource count, large resources. Uses the browser's Performance API. Best called right after navigating to a page. |
| crawl_siteA | Crawl the entire site starting from the current page. Visits all internal links, runs all detectors on each page, and checks links and performance. This is the most thorough scan — it discovers pages automatically and tests everything. Can take 30-120 seconds depending on site size. Args: max_pages: Maximum number of pages to visit (default 20) |
| test_actionA | Click a button/link and automatically verify what changed. Captures state before and after the click, runs all detectors, computes a diff, and takes a screenshot. Returns a complete analysis in one call. Args: element_index: The [N] index of the element to click action_description: What you expect to happen (e.g. "delete the Buy groceries task") |
| test_formA | Fill a form, submit it, and verify the result — all in one call. Matches fields by name/placeholder, types values, clicks submit, then checks if the operation succeeded or failed as expected. Args: form_fields: Dict mapping field name to value. Example: {"email": "test@test.com", "password": "abc123"} submit_text: Text of submit button to click. Auto-detects if empty. submit_index: Element index of submit button. Used if submit_text is empty. expected_result: "success" (expect redirect/success msg), "validation_error" (expect error msg), or "any" |
| test_crudA | Test a complete Create → Verify → Edit → Verify → Delete → Verify cycle. Navigates to the create form, fills it, submits, then verifies the item exists on the list page. Then finds edit/delete buttons and tests those too. Args: create_url: URL of the create/new form (e.g. "/tasks/new") list_url: URL where created items appear (e.g. "/tasks") item_data: Dict of field:value pairs for creating the item item_name_field: Key in item_data that identifies the item (e.g. "title"). Auto-detects if empty. |
| end_sessionA | End the testing session, close the browser, and generate an HTML error report. Returns the path to the generated report and a summary of findings. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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/chriswu727/argus'
If you have feedback or need assistance with the MCP directory API, please join our Discord server