mempalace memory

https://mempalace-mcp.vercel.app/ — Register or sign in here first to create your API key (mpk_...). mempalace memory is the hosted MCP layer from the mempalace (Memory Palace) project: per-user memory drawers (wing/room), semantic search on Cloudflare (D1 + Vectorize + Workers AI embeddings). MCP endpoint: https://glidepath.dpdns.org/mcp . Authenticate with Authorization: Bearer <key> or X-Mempalace-Api-Key (for Smithery Session Config / gateways). MIT license. In-server docs: MCP resources under docs://mempalace-memory/* (getting-started, authentication, tools-reference, data-model, troubleshooting).

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

模型生成摘要（rules/v1 · 2026-09-27 16:22）：https://mempalace-mcp
这是模型对公开材料的总结，不是官方声明，请以原链内容为准。

接入信息

传输形态: http
鉴权方式: 需 API Key（需要配置：mempalace memory API Key）
端点: https://mempalace-memory--farr1102work-bzcc.run.tools

该服务需要凭证，请按官方文档申请后替换占位符

{
  "mcpServers": {
    "mempalace memory": {
      "headers": {
        "Authorization": "Bearer \u003cYOUR_KEY\u003e"
      },
      "url": "https://mempalace-memory--farr1102work-bzcc.run.tools"
    }
  }
}

能力清单

工具	说明
mempalace_status	Summarize the current user's memory palace: total drawers, counts per wing, counts per room. Use when you need grounding before writes or searches, or when the user asks what is stored. Do not use for semantic lookup—use mempalace_search instead. Read-only. Returns JSON in MCP text: { total_drawers, wings: [{ wing, c }], rooms: [{ room, c }] }.
mempalace_add_drawer	Persist a new memory drawer: writes to the user's D1 row, then embeds and upserts to Vectorize for later semantic search. Use when the user wants to remember something long-term (facts, decisions, contacts, meeting notes, checkpoints). Do not use to retrieve data—use mempalace_search. Not idempotent: each call creates a new row. Response JSON: { success, memory_id, wing, room, vectorize: { ok, len?, error? } }; vectorize.ok may be false while the row still saved.
mempalace_search	Search the current user's memories by meaning (Vectorize embeddings), optionally scoped to wing and/or room. Use when answering questions that depend on prior stored context, or before writing to avoid duplicates. Read-only. If the index is still catching up after a recent write, mode may be like_fallback (SQL substring). Response JSON: { query, results: [{ id, text, wing, room, source_file, similarity }], filters: { wing, room }, mode: 'vectorize' \| 'like_fallback' }.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。