io.github.meharajM/agent-loop-mcp

Official

by meharajM · JavaScript

Agentic memory manager. Install Skill: npx skills add meharajM/agent-loop-mcp

agent-loop-mcp MCP Server

The io.github.meharajM/agent-loop-mcp server provides agentic memory management and state persistence for long-running agentic workflows. It is installed via an npx skills command (npx skills add meharajM/agent-loop-mcp) and is positioned as an MCP Server within a two-part ecosystem that includes an Agent Skill.

🛠️ Key Features

Agentic memory manager
Persistent memory and state management for long-running workflows
Supports an open Agent Skills specification (agent skills badge shown)
Two-part ecosystem approach (MCP Server plus Agent Skill)

🚀 Use Cases

Maintain persistence for long-running agentic workflows
Provide state continuity for models with limited context windows

⚡ Developer Benefits

Enables AI models to use persistence similar to higher-end models
Integrates with the Agent Skills/open standard ecosystem

⚠️ Limitations

The provided excerpt does not list specific MCP tools, APIs, or configuration options

Topics

agent-memoryagent-skillsai-agentsautonomous-agentsclaude-codecodexcursorgemini-cligithub-copilotskills-sh

README.md2 KBView on GitHub

Agentic Loop Memory Server ♾️

Agent Skills skills.sh

The industry-standard persistent memory and state manager for long-running agentic workflows.

Enable any AI model—especially smaller ones with limited context windows—to function with the persistence of high-end models. This project works as a two-part ecosystem: an MCP Server for state management and an Agent Skill for orchestration.

🛠 Complete Setup (Required)

For the best experience, you must install both the orchestration skill and the MCP server.

1. Install the Skill

Install the agentic-loop skill into your AI agent (Codex, Claude Code, Cursor, Gemini CLI, GitHub Copilot, and other Agent Skills hosts):

bash

npx skills add meharajM/agent-loop-mcp@agentic-loop -g -y

Preview the skill before activation:

bash

gh skill preview meharajM/agent-loop-mcp agentic-loop

2. Configure the MCP Server

Add the following to your `mcp_config.json`:

json

{
  "mcpServers": {
    "agent-loop": {
      "command": "npx",
      "args": ["-y", "@mhrj/mcp-agent-loop"]
    }
  }
}

🌟 Why this approach is unique

Unlike passive memory tools, this is an Active State Manager. It monitors word counts to trigger compaction cycles and enforces a "Self-Healing Strategy" on every failure, preventing AI agents from getting stuck in mindless loops.

📂 Project Structure

src/: TypeScript source for the MCP server.
skills/agentic-loop/SKILL.md: The instruction manual for the AI.
build/: JavaScript artifacts.

📄 License

ISC

Install

Add to VS Code Add to Cursor

claude_desktop_config.json