Get started with MemQ

Memory that carries work forward

Most memory tools store notes. MemQ turns memory into a living system: it writes, searches, reflects, links ideas, protects namespaces, and routes different memory jobs through the right inference path.

Prompts cannot upgrade themselves. Your Billing Dashboard plan and API key decide access before memory or AI usage is allowed.

Choose a starter repo

Use a starter when you want a working save-to-recall loop instead of a blank config file. Each starter keeps secrets in MEMQ_API_KEYand includes a smoke path for save -> fresh request -> recall.

Agent discovery path

Modern agents do not have to start from a pasted tutorial. The homepage and MemQ page advertise discovery links, and the well-known metadata below points agents to Billing Manager auth, the MemQ MCP server card, OpenAPI descriptions, docs, and status.

# Discover public API and MCP metadata
curl -I https://multinex.ai/
curl -L https://multinex.ai/.well-known/api-catalog
curl -L https://multinex.ai/.well-known/oauth-protected-resource
curl -L https://multinex.ai/.well-known/mcp/server-card.json

# MemQ still connects through the hosted MCP endpoint
curl -I https://mcp.multinex.ai/mcp/v1

Prerequisites

• A Multinex account with a MemQ API key — create one in Billing Manager
• An MCP-capable editor — Claude, Cursor, VS Code, Claude Desktop, or Antigravity

1. Add the API-key MCP config

Paste this into your editor's MCP configuration file and keep MEMQ_API_KEY in your local environment or secret store. For detailed per-editor instructions, see the editor setup guide. Agent-capable clients may also discover the same endpoint from the MCP server card or from the API catalog.

{
  "mcpServers": {
    "memq": {
      "type": "http",
      "url": "https://mcp.multinex.ai/mcp/v1",
      "transport": "streamable-http",
      "headers": {
        "Authorization": "Bearer $MEMQ_API_KEY"
      }
    }
  }
}

Copy-paste MCP snippets

These snippets cover the primary developer surfaces. Keep the API key in your environment or secret manager; do not paste raw keys into config files.

{
  "mcpServers": {
    "memq": {
      "type": "http",
      "url": "https://mcp.multinex.ai/mcp/v1",
      "transport": "streamable-http",
      "headers": {
        "Authorization": "Bearer $MEMQ_API_KEY"
      }
    }
  }
}

{
  "mcpServers": {
    "memq": {
      "type": "http",
      "url": "https://mcp.multinex.ai/mcp/v1",
      "transport": "streamable-http",
      "headers": {
        "Authorization": "Bearer $MEMQ_API_KEY"
      }
    }
  }
}

{
  "mcp": {
    "servers": {
      "memq": {
        "type": "http",
        "url": "https://mcp.multinex.ai/mcp/v1",
        "transport": "streamable-http",
        "headers": {
          "Authorization": "Bearer $MEMQ_API_KEY"
        }
      }
    }
  }
}

{
  "mcpServers": {
    "memq": {
      "type": "http",
      "url": "https://mcp.multinex.ai/mcp/v1",
      "transport": "streamable-http",
      "headers": {
        "Authorization": "Bearer $MEMQ_API_KEY"
      }
    }
  }
}

{
  "serverUrl": "https://mcp.multinex.ai/mcp/v1",
  "transport": "streamable-http",
  "headers": {
    "Authorization": "Bearer $MEMQ_API_KEY"
  }
}

{
  "name": "memq",
  "type": "http",
  "url": "https://mcp.multinex.ai/mcp/v1",
  "transport": "streamable-http",
  "headers": {
    "Authorization": "Bearer $MEMQ_API_KEY"
  }
}

2. Restart and connect

Restart your editor after saving the config. MemQ uses the API key to activate the right plan, namespace access, AI call meters, memory read/write limits, and tool activity visibility.

3. Verify the connection

After approval, your AI auto-discovers all 35 memory tools. Run this verification sequence to confirm everything works:

# 1. Session handshake — confirms auth + namespace
reunion

# 2. Check your namespace and access tier
namespace_info

# 3. Write a test journal entry
journal_record  (content: "First MemQ connection verified")

# 4. Search for it
journal_search  (query: "first connection")

# 5. Pack context for the current session
mnemosyne_context

If all five calls return successfully, you're connected and your AI has persistent memory.

First useful memories

After the test entry works, add one real memory. This gives your agent immediate value and proves the loop before you depend on it.

Next steps