supermemory
Supermemory's universal Memory MCP will save and bring your context everywhere you go - from Claude, Cursor, chatgpt or any AI tool.
What it can do
- 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 pos
- 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 acro
- 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}.
What data it sees
Do you need an account
No: the server works without sign-in
Supermemory's universal Memory MCP will save and bring your context everywhere you go - from Claude, Cursor, chatgpt or any AI tool.
How to connect
How to connect supermemory to Claude
The server address to paste into Claude settings:
https://supermemory.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect supermemory to ChatGPT
The server address to paste into ChatGPT settings:
https://supermemory.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect supermemory to Cursor
The server address to paste into Cursor settings:
https://supermemory.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (4)
Raw names from tools/list. Only developers need these.
| 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 |