limai
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EXA_API_KEY | No | API key for Exa search to improve web search reliability. | |
| TAVILY_API_KEY | No | API key for Tavily search to improve web search reliability. | |
| BRAVE_SEARCH_API_KEY | No | API key for Brave Search to improve web search reliability (otherwise falls back to DDG free backup which may be blocked). |
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 |
|---|---|
| screen_captureA | 擷取本機全螢幕畫面。回傳 PNG 圖片(多模態客戶端可直接看見畫面內容)。僅在明確需要時呼叫。 |
| list_windowsA | 列出前景視窗與所有有標題的視窗(行程名+標題)。輕量了解使用者正在做什麼。 |
| read_clipboardA | 讀取目前剪貼簿文字(上限 2 萬字元)。 |
| heartbeat_nowA | 立即執行一次心跳:收集前景視窗/閒置秒數/剪貼簿變化/todo 數量,寫入 vitals。 |
| vitals_latestB | 最近一次心跳快照。 |
| vitals_historyC | 最近 N 筆心跳歷史。 |
| memory_addB | 新增或更新長期記憶。名稱唯一;keywords 供日後檢索觸發。內容應簡潔、去修辭、客觀(角色記憶規範)。 |
| memory_searchC | 依關鍵字/名稱/內容搜尋記憶。 |
| memory_listB | 列出全部長期記憶。 |
| memory_forgetC | 依名稱刪除一條記憶。 |
| todo_addC | 新增待辦任務(open 狀態;同名 open 任務會拒絕重複)。 |
| todo_listA | 列待辦;status 可選 open/done,省略則全部。 |
| todo_updateC | 標記完成(done)/重開(reopen)/刪除(remove)。id 接受 id 或 name。 |
| web_searchA | DuckDuckGo 公開網頁搜尋,回傳標題/URL/摘要。不執行 JS、不讀結果頁正文。 |
| web_fetchA | 讀取公開 HTTP(S) URL。readable=抽正文、source=原文;offset/limit 有界分頁;拒絕本機與私網位址。 |
| fs_lsB | 列出目錄直屬成員(不遞迴、不讀內容)。 |
| fs_readA | 讀取檔案。文字檔用行範圍;PDF 用 pages 參數(如 "1-5"、"3"),回傳頁面 PNG 圖像內容(預設單次上限 20 頁,含總頁數與續讀位置);fs_edit 前必讀以建立觀測狀態。 |
| fs_writeA | 建立新檔或完整覆蓋(自動建父目錄)。不做局部合併。 |
| fs_editA | 對既有檔案做精確替換。須先 fs_read;old 必須唯一(多處命中需 replace_all 或更多上下文)。 |
| fs_findA | glob 路徑模糊搜尋(跳過 .git/node_modules;不搜尋內容)。 |
| fs_grepA | 正則逐行搜尋檔案內容(跳過 .git/node_modules 與 >1MB 檔)。非法正則時降級為精確字面量:有命中回 literal_fallback 警告,零命中才報 INVALID_REGEX。 |
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 21 tools
Each tool targets a distinct resource and action—monitoring (screen, windows, clipboard, heartbeat), memory (add/search/list/forget), todo (add/list/update), web (search/fetch), and filesystem (ls/read/write/edit/find/grep). There is no meaningful overlap; even fs_write vs fs_edit are clearly separated by create/overwrite vs precise replacement.
All tool names follow a consistent 'domain_action' pattern with snake_case (e.g., memory_add, web_fetch, fs_grep). The verb is consistently after the domain, and every name is lowercase, making the API predictable and easy to navigate.
With 21 tools, the server is slightly above the ideal range but each tool serves a clear purpose across multiple domains (system monitoring, memory, todos, web, filesystem). The count is justified given the broad scope, though a few tools could potentially be consolidated without losing clarity.
The server covers most core operations for its domains—memory and todo have full CRUD-ish coverage, web has search and fetch, and filesystem has read/write/edit/find/grep. However, the absence of a file deletion tool (e.g., fs_delete) leaves the filesystem incomplete, and there is no explicit tool for renaming or moving files. This gap could cause agent failures when cleanup is required.