Agent Locks

Verified Integration

Author: @storing•Category: ServerApplication

GitHub Repository

JSON-RPC 2.0

Protocol Standard

Sub-second

Execution Latency

Active

Operational Status

Client Configuration

— Connect Agent Locks to Claude Desktop or Cursor in seconds

{
  "mcpServers": {
    "agent-locks": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-agent-locks"
      ],
      "env": {}
    }
  }
}

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).

Architecture & Capabilities

System Overview

Coordinates multiple AI coding agents across git worktrees using filesystem-based locks, enabling work claiming, activity visibility, and conflict avoidance without polluting repository history.

Indexed Date

7/21/2026

License

Open Source

Protocol Layer

stdio / SSE RPC

Frequently Asked Questions

Architecture and operational details for Agent Locks

Agent Locks is a filesystem-based, database-free tool designed to coordinate multiple AI coding agents (like Claude Code sessions) across different Git worktrees. Its primary purpose is to enable agents to claim work, maintain visibility into ongoing activities, and avoid file conflicts, all without ever polluting the main repository's Git history.

Related MCP Servers

Browse all servers →

@configuring

0xArchive

Provides comprehensive historical and real-time crypto market data, including orderbooks, trades, candles, and more, from Hyperliquid, HIP-3, and Lighter.xyz.

MCP Server5 FAQs

Learn more

@spawning

0xGasless

Facilitates gasless blockchain transactions and interactions directly from Claude AI conversations.

MCP Server4 FAQs

Learn more

@spawning

0xGasless

Bridges Claude AI with blockchain networks, enabling gasless transactions, swaps, and transfers directly from natural language conversations.

MCP Server5 FAQs

Learn more