ai.workingmemory由 workingmemory.ai 发布官方发布者v1.0.0更新于 Oct 27, 2026
Persistent personal memory for AI assistants — save, search, and recall across every MCP client.
WorkingMemory 是一个远程 MCP 服务器，为助手提供持久化的个人记忆：保存笔记与事实、日后检索，并可删除条目。
Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。
把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。
阅读 https://sourceweft.com/mcp/ai.workingmemory%2Fmemory/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。把它添加到你客户端的 mcpServers 配置中。
{
"mcpServers": {
"workingmemory": {
"type": "http",
"url": "https://app.workingmemory.ai/mcp"
}
}
}Save to memory
Save a thought, insight, fact, or todo to the user's Working Memory. The text is parsed and stored as one or more structured memory items, searchable a moment later via search_memory. Also use this when the user pastes memories or notes brought from another assistant — pass the full pasted text; it is split into individual memories automatically.
text必填clientSearch memory
Search the user's Working Memory for relevant past notes and facts. Use this when the user references something they may have stored earlier, or to find related context before answering. Always include your conversation id in client.conversation_id.
kquery必填clientdedupe_recentconversation_idManage memory
Manage an existing memory item. Currently supports deleting a memory by id (soft delete — recoverable for 30 days). Use search_memory to find the id first.
id必填action必填Capture memory
Capture durable facts from a task you just completed (drafting an email, summarizing a document, making a decision), as a byproduct — the user does nothing. Pass the task output/content; durable facts are extracted and stored automatically. Always include your conversation id in client.conversation_id. Returns immediately; extraction happens in the background.
clienttask_content必填task_description已满足适用检查项的 83%
该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。
请声明包含 README 的 GitHub 仓库，或在 OAuth 受保护资源元数据中提供 resource_documentation。
托管服务按其提供方的条款使用，因此这里不要求许可证。此检查项不计入百分比。
