Memory MCP server
{
"mcpServers": {
"aiakiv-memory": {
"type": "http",
"url": "https://mcp.aiakiv.com/mcp"
}
}
}{
"mcpServers": {
"aiakiv-memory": {
"type": "http",
"url": "https://mcp.aiakiv.com/mcp"
}
}
}{
"mcpServers": {
"aiakiv-memory": {
"type": "http",
"url": "https://mcp.aiakiv.com/mcp"
}
}
}{
"servers": {
"aiakiv-memory": {
"type": "http",
"url": "https://mcp.aiakiv.com/mcp"
}
}
}{
"mcpServers": {
"aiakiv-memory": {
"type": "http",
"url": "https://mcp.aiakiv.com/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 1.0.0
What it does
AiAkiv provides long-term memory for AI agents by storing conversation content as a searchable knowledge graph. It persists context across sessions, folders, and different AI clients, allowing you to save and recall important information over time.
- Save important details from conversations and retrieve them in future sessions without repeating context.
- Build a searchable knowledge graph of project information, decisions, and discussion history across multiple conversations.
- Maintain continuous context when switching between different AI clients or working across different folders.
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.