Mirror Memory MCP Server

io.github.Tr1ckyMag1ca1由 GitHub 帳號 Tr1ckyMag1ca1 發布v1.0.0更新於 Nov 2, 2026

Personal knowledge base MCP server with semantic search, auto-categorization, metadata extraction

發布方自己的服務：Memory.fit

已驗證Streamable HTTP可網頁執行知識與記憶 AI 與機器學習

服務詳細資訊

識別碼: io.github.Tr1ckyMag1ca1/mcp-server
傳輸: Streamable HTTP
執行環境: Web executable
信任: Verified
發布於: Sep 16, 2026

安全提示

MCP 服務會接收對話中的工具呼叫請求，並可能執行外部操作。啟用前請先了解該服務能做什麼，並只授予它所需的權限。

註冊中心已驗證此條目所屬的 GitHub 帳號 Tr1ckyMag1ca1。這並不表明該帳號就是產品方。

SourceWeft 的檢查只涵蓋條目是否完整、端點是否回應；不審查伺服器的程式碼，也不審查其工具的行為。

在 README 中新增徽章

向讀者展示該 MCP 服務已收錄於 SourceWeft，徽章連結到本頁。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.Tr1ckyMag1ca1%2Fmcp-server.svg)](https://sourceweft.com/mcp/io.github.Tr1ckyMag1ca1%2Fmcp-server?utm_source=readme&utm_medium=badge)

概覽

AI 產生的概覽

Mirror Memory 是託管的個人知識庫，讓助理儲存、自動分類並以語意搜尋你的記憶。

可以做什麼: 以語意相似度搜尋記憶，使用使用者問題中的具體詞語
儲存新的想法，由 AI 自動分類並擷取人物、主題、待辦事項與日期
列出可用的記憶分類，並取得最近儲存的記憶
記憶會被向量化、去重，並處於活躍、封存或已被取代的狀態
適用情境: 適合希望助理跨工作階段、跨工具記住你的偏好、目標、人物與想法，並能依意義而非關鍵字回想的情境。
執行需求: 遠端 Streamable HTTP 端點，不需本機執行環境。需要 Mirror Memory 帳號，並在應用程式設定中產生 API 金鑰，透過 Authorization Bearer 標頭傳送。MCP 存取需要付費的 Solo Pro 或 Lifetime 方案。

安裝前請注意

API 金鑰屬於憑證，透過 Authorization 標頭傳送，需妥善保管。儲存的記憶屬個人內容，會傳送給第三方服務；README 稱其只記錄互動事件而不記錄內容。寫入記憶會變更已存資料，且 MCP 存取需要付費訂閱。

安裝

在 SourceWeft 中

開啟儀表板中的 Mirror Memory MCP Server，將其新增到工作區。
為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.Tr1ckyMag1ca1%2Fmcp-server/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "mirror-memory": {
      "type": "http",
      "url": "https://hcelnlqmgddxzvjegpdr.supabase.co/functions/v1/mcp-server"
    }
  }
}

README

Mirror Memory MCP Server

Give your AI a memory. Mirror Memory is a personal knowledge base that lets Claude, ChatGPT, Cursor, and any MCP-compatible AI remember what matters to you — your preferences, experiences, goals, people, and ideas.

Capture thoughts via the web app, Telegram, or directly through MCP tools. Search them semantically. Your AI assistant becomes one that actually knows you.

Website: mirrormemory.ai App: app.mirrormemory.ai

MCP Tools

Tool	Description
`search_memories`	Semantic similarity search across your memories. Use specific terms from the user's question for best results.
`store_memory`	Save a new thought or piece of information. Auto-categorized via AI, auto-extracts people, topics, action items, and dates.
`list_categories`	List all available memory categories (Ideas, Tasks, Notes, People, Work, etc.).
`get_recent_memories`	Retrieve your most recently stored memories.

Quick Setup

1. Get your API key

2. Connect your AI

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

json

{  "mcpServers": {    "mirror-memory": {      "url": "https://hcelnlqmgddxzvjegpdr.supabase.co/functions/v1/mcp-server",      "headers": {        "Authorization": "Bearer YOUR_API_KEY"      }    }  }}

{  "mcpServers": {    "mirror-memory": {      "url": "https://hcelnlqmgddxzvjegpdr.supabase.co/functions/v1/mcp-server",      "headers": {        "Authorization": "Bearer YOUR_API_KEY"      }    }  }}

Claude Code (~/.claude/settings.json):

json

{  "mcpServers": {    "mirror-memory": {      "url": "https://hcelnlqmgddxzvjegpdr.supabase.co/functions/v1/mcp-server",      "headers": {        "Authorization": "Bearer YOUR_API_KEY"      }    }  }}

{  "mcpServers": {    "mirror-memory": {      "url": "https://hcelnlqmgddxzvjegpdr.supabase.co/functions/v1/mcp-server",      "headers": {        "Authorization": "Bearer YOUR_API_KEY"      }    }  }}

Cursor (.cursor/mcp.json):

json

{  "mcpServers": {    "mirror-memory": {      "url": "https://hcelnlqmgddxzvjegpdr.supabase.co/functions/v1/mcp-server",      "headers": {        "Authorization": "Bearer YOUR_API_KEY"      }    }  }}

{  "mcpServers": {    "mirror-memory": {      "url": "https://hcelnlqmgddxzvjegpdr.supabase.co/functions/v1/mcp-server",      "headers": {        "Authorization": "Bearer YOUR_API_KEY"      }    }  }}

Windsurf, Cline, or any MCP client — use the same URL and API key pattern above.

3. Start talking

Once connected, your AI will automatically search your memories for relevant context and store new information you share. No special commands needed.

How It Works

You say something → AI calls store_memory → embedded + categorized + metadata extracted → storedYou ask something → AI calls search_memories → semantic vector search → relevant memories returned

You say something → AI calls store_memory → embedded + categorized + metadata extracted → storedYou ask something → AI calls search_memories → semantic vector search → relevant memories returned

Every memory is:

Embedded as a 1536-dim vector for semantic search
Auto-categorized into one of 12+ categories via AI
Metadata-enriched — people mentioned, action items, topics, dates, and knowledge type are extracted automatically
Deduplicated via SHA-256 content fingerprinting