Get Context Digest
get_context is one of the 32 MCP tools in Weft, the AI task manager you run by talking to Claude, Cursor, Codex or ChatGPT through one MCP endpoint. The workspace's live decisions and lessons, packed to a token budget, newest first — what an agent should read before starting anything non-trivial. Derived from recorded decisions rather than authored as a document, so it cannot rot: a superseded decision drops out the moment its replacement is recorded, and every line carries its date. Scope it to a project or a task to narrow it; lines that do not fit the budget are counted, never silently hidden.
Weft 是為獨立創業者和小團隊打造的 AI 任務管理工具。
工具參考文件以英文維護：工具名稱、參數與範例在每種語言中都相同。
參數
| 名稱 | 型別 | 必填 | 說明 |
|---|---|---|---|
| project | string | 否 | Narrow to one project — name (case-insensitive) or id. |
| taskId | uuid | 否 | Narrow to decisions recorded about one task. |
| budgetTokens | integer | 否 | How much context the caller can afford. Default 800. |
回傳
scope, budgetTokens, lines[] (one dated line per live decision), and omitted — how many did not fit.
註記
- 唯讀。這個工具不會變更伺服器狀態，可以安全地自動呼叫。
範例
使用者說的話：
"Before you start: what has already been decided about this project?"相關
- 全部 32 個 MCP 工具 — 目錄檢視。
- 梭子 — AI 客戶端如何使用這些工具。
- 用你自己的客戶端呼叫這個工具：參考設定指南，或直接打
https://letsweft.com/api/mcp。