Quick Start

Get MemPad running with your AI assistant in under 5 minutes.

Prerequisites

  • An MCP-compatible AI client (Claude Code, Gemini CLI, Codex, Cursor, or Cline)
  • A MemPad account (request access if you don't have one)

Step 1: Add MemPad to Your Client

Add MemPad as an MCP server in your client's configuration:

Add MemPad using the CLI:

claude mcp add --transport http mempad https://api.mempad.ai/mcp

That's it! Claude Code has native OAuth support.

Add MemPad to your Gemini CLI settings:

# In ~/.gemini/settings.json
{
  "mcpServers": {
    "mempad": {
      "url": "https://api.mempad.ai/mcp"
    }
  }
}

Gemini CLI has native OAuth support - no extra setup needed.

First, enable experimental HTTP MCP support:

# In ~/.codex/config.toml
experimental_use_rmcp_client = true

[mcp_servers.mempad]
type = "http"
url = "https://api.mempad.ai/mcp"

Then authenticate:

codex mcp login mempad

Cursor requires mcp-proxy for HTTP MCP servers. First install it:

npm install -g mcp-proxy

Then add to your Cursor MCP config (~/.cursor/mcp.json):

{
  "mcpServers": {
    "mempad": {
      "command": "mcp-proxy",
      "args": ["--transport=streamablehttp", "https://api.mempad.ai/mcp"]
    }
  }
}

Add to your Cline settings in VS Code:

{
  "mcpServers": {
    "mempad": {
      "url": "https://api.mempad.ai/mcp",
      "type": "streamableHttp"
    }
  }
}

OAuth will trigger automatically when the server requires authentication.

Step 2: Restart Your Client

Close and reopen your AI client to load the new MCP server configuration.

Step 3: Authorize MemPad

The first time you use MemPad, you'll be prompted to authorize via your browser. Sign in with the email and password you received when your access was approved.

Step 4: Start Using MemPad

That's it! You can now use these commands with your AI:

mp!

Load your memory into the conversation

mp:

Save the current context to your memory

Example Conversation

You: mp!
AI: I've loaded your memory. I can see you prefer TypeScript,
you're working on a React project, and you like concise responses.
How can I help you today?

You: I'm also learning Rust now. Update my memory.
AI: Got it! I've added that you're learning Rust to your
memory. mp:

You: [Later, in a new conversation] mp!
AI: Welcome back! I see you prefer TypeScript, you're
working on a React project, you like concise responses, and
you're learning Rust...

Next Steps