kimi-webbridge-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WEBBRIDGE_URL | No | The URL of the WebBridge daemon. | http://127.0.0.1:10086 |
| WEBBRIDGE_SESSION | No | The default session name. | grok-webbridge |
| WEBBRIDGE_TIMEOUT_MS | No | The timeout in milliseconds for WebBridge operations. | 120000 |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| wb_statusA | Check WebBridge daemon + browser extension connection. Call first if unsure whether the bridge is ready. |
| wb_navigateA | Open or navigate to a URL in the real browser. First call of a task should pass group_title. Use newTab:true when pages should coexist. |
| wb_go_backB | Browser history back (Claude-in-Chrome style navigation helper). |
| wb_go_forwardC | Browser history forward. |
| wb_reloadA | Reload the current page. hard:true bypasses cache when CDP allows. |
| wb_find_tabA | Select a tab as current. URL match is fuzzy within the session (trailing slash/query tolerant). active:true borrows the focused session tab when possible. |
| wb_list_tabsA | List tabs belonging to the current session (tab group). |
| wb_close_tabB | Close the current tab in the session. |
| wb_close_sessionA | Close ALL tabs in the session/group. Only when the user asks to clear agent tabs. |
| wb_snapshotA | Accessibility tree with @e refs (like Claude read_page). Prefer before click/fill. |
| wb_get_textA | Extract visible page text (like Claude get_page_text). Better than full snapshot for articles. |
| wb_findA | Search the accessibility tree by text/role (like Claude find). Returns matching @e refs when present. |
| wb_waitA | Wait until text appears, CSS selector matches, or document is ready (timeout). |
| wb_clickA | Click an element (@e ref preferred, or CSS). By default, if the click opens a new session tab, switches current tab to it (Bilibili 动态/收藏 style). |
| wb_fillA | Clear-and-fill input/textarea/contenteditable. selector = @e or CSS. |
| wb_press_keyC | Press a key or combo on the focused element (e.g. Enter, Escape, Tab, Control+A). Like Claude press_key. |
| wb_scrollA | Scroll page or element into view. direction: up|down|left|right, or x/y deltas, or selector/@e into view. |
| wb_evaluateB | Run JavaScript in the page. Prefer compact JSON.stringify returns. Wrap multi-call state in an IIFE. |
| wb_screenshotA | Screenshot current tab (or selector). Default format=jpeg for reliability; auto-retries smaller jpeg on timeout. Returns path; embeds image when under size cap. Errors include problem+hint. |
| wb_networkB | Capture/list network requests. cmd: start | stop | list | detail. |
| wb_consoleA | Capture page console / errors (Claude-style). cmd: start (install interceptor) | list | clear | stop. |
| wb_uploadA | Set files on a file input element. files must be absolute local filesystem paths (not http/data URLs). Page must already show . |
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 22 tools
Each tool targets a distinct browser concern: history, tab/session management, page reading, interaction, and capture. Even similar readers like wb_snapshot, wb_get_text, and wb_find are explicitly differentiated by intended use and output type.
All tools share a consistent wb_ prefix and snake_case style, but a few names such as wb_status, wb_network, and wb_console are nouns rather than verb_noun commands. This is a minor deviation from the otherwise predictable pattern.
22 tools is above the typical compact range, but the broad browser-automation domain justifies most entries with little duplication. It feels slightly heavy rather than bloated or sparse.
The tool surface covers the full browser workflow: connection checking, navigation, tab lifecycle, page reading, interaction, waiting, screenshots, network/console capture, and upload. Minor gaps like dedicated cookie or dropdown helpers exist, but agents can work around them with wb_evaluate.