Getting Started

Recordari gives your AI agents a memory that persists across sessions. Instead of starting every conversation from scratch, your agent loads its memory at the start of a session and picks up exactly where it left off - with context about past decisions, active constraints, and recent work.

This page gets you from zero to a working connection in five minutes.

What you need

• A Recordari account - sign up at recordar.io
• An MCP-compatible AI agent: Claude Code, Claude.ai, or any client that supports the Model Context Protocol

Step 1 - Get an API key

After signing up, open the dashboard and go to API Keys. Click New key, give it a name (e.g. "Claude Code - my-project"), and copy the value immediately. You won't be able to see it again.

Step 2 - Connect your agent

Claude Code

Create .mcp.json at the root of your project:

{
  "mcpServers": {
    "recordari": {
      "type": "http",
      "url": "https://api.recordar.io/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Add .mcp.json to your .gitignore before committing. Then reload Claude Code - Recordari should appear in your active MCP servers.

Claude.ai

Go to Settings → Integrations → Add integration, and enter:

• URL: https://api.recordar.io/mcp
• Authorization: Bearer YOUR_API_KEY

Note: Claude.ai connector support requires OAuth 2.1, which is coming soon. Bearer token integration is available now via Claude Code.

Step 3 - Start your first session

Tell your agent to orient on a domain. A domain is just a named bucket for a set of memories - use your project name:

"Orient on the backend-api domain."

On the first call the domain is empty, so you'll get a minimal response. That's fine - we're about to fill it.

Step 4 - File your first memory

Now tell your agent to remember something:

"File a memory that we're using PostgreSQL as the main database. Why it matters: all data access patterns and migration tooling depend on this choice."

Your agent will file the memory and return an ID for it. That decision is now stored, searchable, and connected to everything else your agent learns about this project.

Step 5 - Start the next session

Open a completely new conversation. Tell your agent:

"Orient on the my-project domain."

This time it will come back with your PostgreSQL decision in context. That's it - persistent memory is working.

Where to go next

• Authentication - key types, scopes, rotation
• MCP Tools Reference - every tool with examples
• Pricing & Limits - what each plan includes
• Guide: Using Recordari with Claude Code - a full working session walkthrough