Browser Runtime MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_browser_errorsA | 取得瀏覽器 runtime 錯誤(uncaught exceptions + unhandled promise rejections)。包含 error message、stack trace、發生位置的 DOM context。 |
| get_console_logsB | 取得瀏覽器 console 輸出(error / warn / log 三個等級)。 |
| get_page_infoA | 列出 extension 目前追蹤到的頁面(URL + title + 最後活動時間)以及緩衝區統計。 |
| clear_buffersA | 清空錯誤與 log 緩衝區。用於排除舊雜訊後重新觀察。 |
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 4 tools
Each tool has a clearly distinct purpose: browser errors (uncaught exceptions/promise rejections), console logs (all console levels), page info with buffer stats, and buffer clearing. No overlap exists between these four functions.
All tool names follow a consistent verb_noun pattern: get_browser_errors, get_console_logs, get_page_info, clear_buffers. The verb is uniform (get/clear) and the nouns are descriptive.
Four tools is well-scoped for a browser runtime diagnostics server. Each tool covers a distinct aspect of observation and maintenance without redundancy or bloat.
The surface covers error retrieval, log retrieval, page tracking, and buffer management—a complete monitoring lifecycle. A minor gap is lack of subscription or filtering capabilities, but not essential for the stated purpose.