Agentloopkit

Overview

Agentloopkit is a read-only Model Context Protocol server that gives AI assistants direct access to AgentLoopKit tasks, policies, reports, handoffs, and status. Instead of switching between tools and copy-pasting, your AI assistant can query this information directly as callable resources.

The server runs locally on your machine via the npm package agentloopkit, speaking MCP over stdio. It requires no credentials and works immediately after installation. Version v1.2.0 is available now under the MIT license, with source code at abhiyoheswaran1/AgentLoopKit on GitHub.

Agentloopkit is listed in the AI & Agents category and works with any MCP client including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this server, claim the listing to verify ownership and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "agentloopkit": {
      "command": "npx",
      "args": [
        "-y",
        "agentloopkit"
      ]
    }
  }
}