Supermemory MCP Server
Give your AI agents persistent memory — store, recall, and connect facts across every conversation.
Updated
What is Supermemory MCP?
The Supermemory MCP server is a Model Context Protocol server that gives AI assistants persistent memory — letting them store, retrieve, and connect facts across conversations and applications.
Supermemory acts as a universal memory layer for LLMs, solving the problem of agents forgetting context between sessions. It can save new memories, run semantic search to recall relevant ones, and build up a user profile from what it has stored. The service is vendor-hosted on Cloudflare's platform, so there is nothing to deploy yourself — you connect to the remote endpoint at https://mcp.supermemory.ai/mcp.
Authentication uses OAuth by default: your MCP client discovers the authorization server automatically and prompts you to sign in with a Supermemory account. Programmatic access via an API key (prefixed sm_, from app.supermemory.ai) is also supported.
Tools the Supermemory MCP server exposes
| Tool | What it does |
|---|---|
| memory | Save (or forget) information to Supermemory; ingestion into the search index is eventually consistent. |
| recall | Run semantic search over stored memories and optionally retrieve the user profile. |
Connect the Supermemory MCP server
Claude Code
- 1
Add the remote server
Run: claude mcp add --transport http supermemory https://mcp.supermemory.ai/mcp
- 2
Authenticate via OAuth
On first use, Claude Code opens the Supermemory OAuth flow in your browser — sign in to authorize access.
- 3
Verify
Run /mcp in Claude Code to confirm the supermemory server is connected and its memory/recall tools are listed.
Cursor
- 1
Run the installer
npx install-mcp https://mcp.supermemory.ai/mcp --client cursor --oauth yes
- 2
Complete OAuth
The CLI launches the Supermemory OAuth flow; sign in to authorize. You can also add the server manually in ~/.cursor/mcp.json.
- 3
Confirm in Cursor
Open Cursor Settings → MCP and check that supermemory shows as connected.
Sample use cases
After a meeting, an agent saves the key decisions and action items using the memory tool
The notes are indexed and searchable by topic, so anyone can recall what was decided weeks later.
Before answering a question, an agent calls recall to search for relevant prior context
It retrieves related memories and incorporates them into the response, giving accurate answers grounded in past conversations.
An agent maintains a user profile by saving preferences and context with the memory tool
On future interactions, recall retrieves the profile so the agent can personalize responses without asking repeat questions.
A researcher saves key findings from multiple documents using the memory tool throughout the day
Later, recall returns the most relevant findings by topic — acting as a personal knowledge base searchable by meaning, not just keywords.
An agent logs a daily project update with the memory tool after each work session
A weekly recall query returns all progress entries, making it easy to compile a status report without manual note-taking.
An agent saves an architectural decision record (the decision, rationale, and alternatives considered)
Months later, recall surfaces the original reasoning when someone asks why a technical choice was made.
An agent uses the memory tool's forget capability to remove outdated or incorrect information
The knowledge base stays clean — recall no longer returns stale data, preventing outdated context from influencing future responses.
Security & permissions
Supermemory MCP uses OAuth by default — your MCP client discovers the authorization server and prompts you to sign in with a Supermemory account, so the agent acts within your account's memory scope (memories can be organized per project). An API key (sm_…, from app.supermemory.ai) can be passed in the Authorization header for programmatic access instead. The agent can read and write your stored memories and the auto-generated profile, so treat the connected account and key as sensitive.
Using Supermemory MCP with Gamut
In a Gamut workflow, an agent can use Supermemory as a connected tool to give automated, event- or schedule-triggered runs durable context. Gamut manages the OAuth connection, so a scheduled or webhook-triggered agent can call recall to pull relevant prior facts before acting and memory to persist new outcomes — letting recurring jobs build on what earlier runs learned instead of starting cold each time.
Frequently asked questions
What is the Supermemory MCP server?
It is a Model Context Protocol server that gives AI assistants persistent memory. It exposes a memory tool to store facts and a recall tool to semantically search them, so agents retain context across conversations and apps. It is hosted by Supermemory at https://mcp.supermemory.ai/mcp.
Is the Supermemory MCP server free?
Yes — Supermemory's free tier ($0/month, roughly $5 of monthly usage) includes the MCP server. Heavier or production use moves to usage-based paid plans (Pro $19/mo, Max $100/mo, Scale $399/mo) and custom Enterprise.
How do I connect Supermemory MCP to Claude or Cursor?
For Claude Code, run claude mcp add --transport http supermemory https://mcp.supermemory.ai/mcp and complete the OAuth sign-in. For Cursor, run npx install-mcp https://mcp.supermemory.ai/mcp --client cursor --oauth yes (or add the URL in ~/.cursor/mcp.json).
Is Supermemory MCP hosted or self-hosted?
The MCP server is vendor-hosted on Supermemory's Cloudflare-based infrastructure — you connect to the remote endpoint with OAuth, nothing to deploy. Self-hosted and air-gapped deployments are available on the Enterprise plan.
How does Supermemory's semantic search work?
The recall tool uses semantic search — it matches by meaning, not just keywords. So a query about 'deployment process' will find memories about 'release workflow' or 'shipping to production' even if those exact words weren't used.
Can I delete specific memories from Supermemory?
Yes. The memory tool supports a forget operation that removes specific stored information, keeping your knowledge base clean and preventing stale data from affecting future searches.
Does Supermemory support user profiles?
Yes. The recall tool can optionally retrieve a stored user profile alongside search results, enabling personalized agent interactions based on saved preferences and context.