Brijio MCP server for AI agent browser resources and tools. Gives AI agents controlled, user-approved browser access.
Brijio MCP server has 16 tools with complete input schemas and descriptions. Naming follows verb_noun convention (perform_batch, capture_screenshot, click_element). Descriptions are present but brief (avg ~80 chars, below the 194-char baseline). Parameters are typed and mostly described, but lack depth on constraints, formats, and dependencies. Output schemas are not documented. Error handling is minimal, no recovery guidance or actionable error messages visible. Tools are well-composed (single responsibility) and support browser automation workflows. Missing: pagination guidance, output schema documentation, and detailed parameter constraints.
Capture a screenshot of the current page or specified tab.
Click an element on the current page by its identifier.
Initiate a file download from a URL.
Get the status of file downloads.
Fetch a resource from a URL with optional size and timeout limits.
Fill text content in an editable element (contenteditable).
Fill a text input field on the current page.
List available browser instances.
Output schemas not documented. LLMs cannot infer what fields each tool returns, forcing them to guess downstream field names and risking broken tool chains.
Descriptions are too brief (avg ~80 chars vs 194-char baseline). Missing WHEN to use each tool, prerequisites, and dependencies. E.g., 'Perform a batch of actions' does not explain when to use perform_batch vs individual action tools.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 56 | 2026-07-28+ | v2 |
List all open tabs in a browser instance.
Navigate the current tab to a specified URL.
Open a new tab in the browser with a specified URL.
Perform a batch of actions on the current page, with optional continuation on error and reading after actions.
Select options from a dropdown or multi-select control.
Set the checked state of a checkbox or radio button.
Submit a form on the current page.
Upload a file to a file input control on the current page.
Parameter constraints not documented. E.g., perform_batch says 'Maximum 20 actions' but does not specify action object structure, valid 'type' enum values, or required fields. LLMs cannot validate inputs without explicit constraints.
No error handling guidance. Tools do not document what errors can occur, whether they are retryable, or what the LLM should do next. E.g., click_element may fail if element not found, but no recovery path is provided.
Parameter descriptions lack format and range guidance. E.g., 'maxSizeBytes' in fetch_resource has no min/max bounds; 'fetchTimeout' has no guidance on reasonable values. LLMs may pass absurd values (0, 999999999) without constraints.