Mem0 MCP

Prerequisites

Mem0 Platform account (Sign up here)
API key (Get one from dashboard)
Node.js 18+ (for npx)
An MCP-compatible client (Claude, Claude Code, Codex, Cursor, Windsurf, VS Code, OpenCode)

What is Mem0 MCP?

MCP (Model Context Protocol) is a standard way for AI clients to call external tools. The Mem0 MCP server hands your agent a set of memory tools, so it can decide for itself when to save something, look something up, or update what it already knows. Nothing runs on your machine: the server is hosted by Mem0, and your client connects to it over HTTPS. Memories you store this way live in your Mem0 account, not on your computer.

Quick setup

Point your clients at the hosted server with a single command:

npx mcp-add \
  --name mem0-mcp \
  --type http \
  --url "https://mcp.mem0.ai/mcp" \
  --clients "claude,claude code,cursor,windsurf,vscode,opencode"

mcp-add is a helper that writes the Mem0 server into each client’s own MCP config file, so you do not have to edit them by hand. Name only the clients you actually use. If you would rather see the change yourself, every client’s manual config is under Client-specific setup. Restart each client afterwards so it picks up the new server.

Signing in

The server is authenticated, so connecting is not enough on its own. There are two ways in:

Sign in through the client
Use your API key

Most clients handle this for you. The first time your agent uses a Mem0 tool, the client opens a browser window asking you to authorize access to your Mem0 account. Approve it once and the client stores the token, refreshing it as needed.This is the easier path, and it is what happens by default if you followed the quick setup above.

If neither is set up, the server replies 401 Authentication required and your client reports the connection as failed.

Available tools

The MCP server exposes these memory tools to your AI client:

Tool	Description
`add_memory`	Save text or conversation history for a user/agent
`search_memories`	Semantic search across existing memories with filters
`get_memories`	List memories with structured filters and pagination
`get_memory`	Retrieve one memory by its `memory_id`
`update_memory`	Overwrite a memory’s text and/or metadata after confirming the ID
`delete_memory`	Delete a single memory by `memory_id`
`delete_all_memories`	Bulk delete all memories in scope
`delete_entities`	Delete a user/agent/app/run entity and its memories
`list_entities`	Enumerate users/agents/apps/runs stored in Mem0
`list_events`	List memory operation events with filters and pagination
`get_event_status`	Check the status of an async memory operation by `event_id`

Client-specific setup

You can also configure individual clients:

Claude Desktop

npx mcp-add \
  --name mem0-mcp \
  --type http \
  --url "https://mcp.mem0.ai/mcp" \
  --clients "claude"

Or manually add to your Claude Desktop configuration (claude_desktop_config.json):

{
  "mcpServers": {
    "mem0-mcp": {
      "type": "http",
      "url": "https://mcp.mem0.ai/mcp"
    }
  }
}

Claude Code

npx mcp-add \
  --name mem0-mcp \
  --type http \
  --url "https://mcp.mem0.ai/mcp" \
  --clients "claude code"

Codex

Direct MCP (fastest, MCP only). Codex reads MCP servers from ~/.codex/config.toml as TOML (not JSON). Add:

[mcp_servers.mem0]
url = "https://mcp.mem0.ai/mcp"
bearer_token_env_var = "MEM0_API_KEY"

Export MEM0_API_KEY in the shell you launch Codex from, then restart Codex. codex mcp add only supports stdio servers, so HTTP servers must be added via config.toml directly, or via the Plugins → Connect to a custom MCP → Streamable HTTP UI in the Codex app.

Codex uses the server name mem0 (not mem0-mcp like the other clients on this page) so it matches the name the bundled plugin registers if you ever sideload it later.

Sideloaded plugin (full experience). If you want the memory protocol skill, Mem0 SDK skill, and opt-in lifecycle hooks alongside the MCP server, sideload the plugin from a clone of mem0ai/mem0. The repo ships a marketplace manifest at .agents/plugins/marketplace.json, so you can register it with one CLI call:

git clone https://github.com/mem0ai/mem0.git ~/codex-plugins/mem0-source
codex plugin marketplace add ~/codex-plugins/mem0-source

Then run codex and /plugins, browse the Mem0 Plugins marketplace, and install Mem0. Don’t combine this with the Direct MCP setup above; the sideloaded plugin auto-registers mem0 via .codex-mcp.json, so a manual [mcp_servers.mem0] block would create a duplicate.See the Codex integration guide for full details, lifecycle-hook setup, and management commands (codex plugin marketplace upgrade / remove).

Cursor

npx mcp-add \
  --name mem0-mcp \
  --type http \
  --url "https://mcp.mem0.ai/mcp" \
  --clients "cursor"

Or go to Cursor → Settings → MCP and add:

{
  "mcpServers": {
    "mem0-mcp": {
      "type": "http",
      "url": "https://mcp.mem0.ai/mcp"
    }
  }
}

Windsurf

npx mcp-add \
  --name mem0-mcp \
  --type http \
  --url "https://mcp.mem0.ai/mcp" \
  --clients "windsurf"

VS Code

npx mcp-add \
  --name mem0-mcp \
  --type http \
  --url "https://mcp.mem0.ai/mcp" \
  --clients "vscode"

OpenCode

npx mcp-add \
  --name mem0-mcp \
  --type http \
  --url "https://mcp.mem0.ai/mcp" \
  --clients "opencode"

Check that it worked

Restart your client, then ask it to store something and read it back in a later message:

You:   Remember that I prefer TypeScript over JavaScript for new projects.
Agent: Saved.

You:   What language do I prefer for new projects?
Agent: You prefer TypeScript over JavaScript.

The second answer only works if the memory was really stored, so this is a genuine round-trip test rather than the model repeating itself. Two things to look for while you do it:

Your client should show the Mem0 tools among its available tools. Most clients list them in a tools or MCP panel.
The first tool call should trigger the browser sign-in described above, unless you configured an API key.

To confirm from outside the client, open the Mem0 dashboard: anything the agent saved appears there.

Troubleshooting

What you see	What it means	What to do
`401` or “Authentication required”	The client connected but is not signed in	Complete the browser sign-in, or set your API key as a bearer token
”Connection refused” or “failed to connect”	The client cannot reach the server	Check your internet connection, then confirm the URL is exactly `https://mcp.mem0.ai/mcp`
The agent has no Mem0 tools	The config was written but the client has not reloaded it	Restart the client. If the tools are still missing, check that `mcp-add` wrote to the config file your client actually reads
`npx: command not found`	Node.js is not installed	Install it from nodejs.org
”Invalid API key”	The key is wrong, revoked, or from a different account	Get a new one from the Mem0 dashboard

Next steps

Platform quickstart: call Mem0 from your own code instead of through an agent
Mem0 CLI: the same operations from your terminal
MCP specification: the Model Context Protocol standard
Gemini with Mem0 MCP: a worked example

Getting Started

Core Concepts

Features

Support

Migration

What is Mem0 MCP?

Quick setup

Signing in

Available tools

Client-specific setup

Check that it worked

Troubleshooting

Next steps

​What is Mem0 MCP?

​Quick setup

​Signing in

​Available tools

​Client-specific setup

​Check that it worked

​Troubleshooting

​Next steps

What is Mem0 MCP?

Quick setup

Signing in

Available tools

Client-specific setup

Check that it worked

Troubleshooting

Next steps