Adaptive Recall

Overview

Adaptive Recall is a Model Context Protocol (MCP) server: Adaptive memory system with cognitive scoring, knowledge graph, and self-improving ML. In practice that means any MCP-compatible AI assistant can call Adaptive Recall's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the npm package adaptive-recall speaks MCP over stdio on your machine. Configuration happens through environment variables — you'll need ADAPTIVE_RECALL_API_KEY. The current release is v1.0.1, published under the MIT license, with source at AIAppsAPI/adaptive-recall on GitHub.

Adaptive Recall is listed under Memory on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Adaptive Recall for AIAppsAPI, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "adaptive_recall": {
      "command": "npx",
      "args": [
        "-y",
        "adaptive-recall"
      ],
      "env": {
        "ADAPTIVE_RECALL_API_KEY": "<adaptive-recall-api-key>"
      }
    }
  }
}

Requires ADAPTIVE_RECALL_API_KEY