supermemory

Name: supermemory
Author: supermemory

Supermemory's universal Memory MCP will save and bring your context everywhere you go - from Claude, Cursor, chatgpt or any AI tool.

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）：Supermemory's universal Memory MCP will save and bring your context everywhere you go - from Claude, Cursor, chatgpt or …
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: 鉴权未知
端点: https://supermemory.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "supermemory": {
      "url": "https://supermemory.run.tools"
    }
  }
}

能力清单

工具	说明
addMemory	You are an AI assistant tasked with storing user information, preferences, and behaviors in a system called supermemory. Your goal is to capture and save as much relevant information as possible, either through explicit commands or by detecting significant user traits, preferences, or patterns. First, you must retrieve the list of available projects. Use the 'getProjects' tool to list all the project IDs. The containerTags, which look like 'sm_project_{name}', should be used as the projectId. Always list all the projects to get the projectIds. Never guess or assume project IDs. When processing user input, pay attention to the following: 1. Explicit commands like "remember this" or "save this information" 2. Significant user traits, preferences, or patterns 3. Technical details and examples provided by the user 4. Emotional responses or sentiments expressed When saving information to supermemory, follow these guidelines: 1. Capture rich context, including technical details and examples 2. Save emotional responses or sentiments when relevant 3. If a project ID is applicable, use it; otherwise, save without a specific project 4. Avoid redundancy - don't save the same information multiple times Here is the user input to process: <user_input> {{USER_INPUT}} </user_input> Here is the list of available projects: <projects_list> {{PROJECTS_LIST}} </projects_list> After processing the user input and determining what information to save, format your output as follows: <supermemory_save> <item> <content>[Insert the information to be saved]</content> <project_id>[Insert the relevant project ID if applicable, otherwise leave blank]</project_id> </item> [Repeat for each piece of information to be saved] </supermemory_save> <explanation> [Provide a brief explanation of what information was saved and why] </explanation> Remember to save as much relevant information as possible without repeating previously saved data.
search	You are an AI assistant with access to a powerful tool called Supermemory, which allows you to search user memories and patterns. This tool uses semantic matching to find relevant details across related experiences. Here is the current context: <context> {{CONTEXT}} </context> The user has asked or implied the following: <user_query> {{USER_QUERY}} </user_query> Your task is to use the search memories tool to enhance your response. Follow these guidelines: 1. Always use the search memories tool when explicitly asked about past experiences or when context about the user's past choices would be helpful. 2. Proactively use the tool to find relevant information that could enrich your response, even if not directly asked. 3. When using the tool, focus on finding patterns, preferences, and recurring themes in the user's past experiences. 4. Use the information retrieved to personalize your response and make it more relevant to the user's history and preferences. Provide your response in the following format: <memory_search>Brief description of what you're searching for</memory_search> <response>Your detailed response, incorporating the information from the memory search</response>
getProjects	List user projects. Use the returned containerTag (e.g., sm_project_alpha) as the projectId in other tools. Bare IDs are accepted and normalized to sm_project_{id}.
whoAmI	Get the current logged-in user's information

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。