Agent Memory vs AI Eval

In-depth architectural comparison of the Agent Memory and AI Eval MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.

Which MCP Server Should You Choose?

Choose Agent Memory when:

• You need dedicated capabilities in the Cloud Platforms domain.
• You prefer local stdio subprocess transport architecture.
• Your security boundary fits: No auth required (Free / Open Source).

Explore Agent Memory Details

Choose AI Eval when:

• You need dedicated capabilities in the Cloud Platforms domain.
• You prefer local stdio subprocess transport architecture.
• Your security boundary fits: No auth required (Free / Open Source).

Explore AI Eval Details

Feature & Specification Comparison

Specification	Agent Memory Cloud Platforms	AI Eval Cloud Platforms
Summary	Cloudflare Workers MCP server: agent-memory	Cloudflare Workers MCP server: ai-eval. REST + MCP (JSON-RPC 2.0). Live: api.lazy-mac.com/ai-eval
Category & Scope	Cloud Platforms	Cloud Platforms
Quality signal

Tools & Capabilities Breakdown

Ready-to-Paste Client Configurations

Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).

{
  "mcpServers": {
    "agent-memory-4": {
      "command": "npx",
      "args": [
        "-y",
        "agent-memory-4"
      ]
    }
  }
}

{
  "mcpServers": {
    "ai-eval": {
      "command": "npx",
      "args": [
        "-y",
        "ai-eval"
      ]
    }
  }
}

Related MCP Server Comparisons