Jev Browser Bridge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TYPESAFE_API_KEY | Yes | TypeSafe Jev API key (or Vercel AI Gateway key with access to Jev). | |
| TEXT_MODEL_API_KEY | Yes | API key for the text helper model (e.g., OpenRouter key). |
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_new_tabB | Open a new browser tab. Returns the new tab's targetId. |
| browser_gotoB | Navigate the current tab to |
| browser_page_infoA | Return current tab metadata: url, title, viewport and scroll sizes. |
| browser_clickB | Click at screen coordinates (x, y). |
| browser_typeC | Insert text into the focused element. |
| browser_fillC | Fill an input matched by |
| browser_pressC | Press a key. |
| browser_scrollA | Scroll the wheel at (x, y) by |
| browser_screenshotB | Capture a PNG screenshot. If |
| browser_list_tabsA | List open page tabs. |
| browser_current_tabA | Return the active tab's targetId, url and title. |
| browser_switch_tabC | Switch to tab by |
| browser_close_tabA | Close a tab. Without |
| browser_ensure_real_tabA | Switch to a real (non-internal) tab if the current one is chrome:// or stale. |
| browser_waitB | Wait for |
| browser_wait_for_loadC | Wait until the current tab's readyState is 'complete'. |
| browser_wait_for_elementB | Wait for an element matching |
| browser_jsA | Evaluate a JavaScript expression in the current tab (or an iframe |
| browser_cdpB | Call a raw Chrome DevTools Protocol method. |
| browser_upload_fileC | Set files on a file input matched by |
| browser_http_getA | HTTP GET |
| browser_start_recordingC | Start recording actions to a local directory. |
| browser_stop_recordingA | Stop the active recording and return its directory. |
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 23 tools
Tools are largely distinct, with clear prefixes and domain-specific actions. Minor overlap exists between browser_type (focused element) and browser_fill (selector-based), and between browser_goto and browser_http_get, but descriptions mostly disambiguate them.
All tools share the browser_ prefix and lowercase snake_case, creating a predictable style. A few names are noun-like rather than verb-first (browser_page_info, browser_current_tab, browser_js, browser_cdp), so it is not perfectly uniform.
23 tools is on the heavier side and crosses into 'feels heavy' territory, though most operations are legitimate browser actions. The wait variants and raw CDP/JS escape hatches add some redundancy, making the set slightly larger than ideal.
The set covers core browser automation workflows: navigation, tabs, input, waiting, screenshots, uploads, recording, JS evaluation, and raw CDP. Missing conveniences like back/forward/reload and more advanced DOM inspection can be worked around via browser_js or browser_cdp.