Sync MCP server configs and rules across AI coding agents

agentsync

Sync MCP server configs and rules across AI coding agents.

The Problem

You use multiple AI coding agents — Claude Code, Cursor, Codex, Cursor. Each stores MCP server configs in its own format (JSON, TOML) and its own location. Keeping them in sync manually is tedious and error-prone.

The Solution

agentsync takes a single source of truth (your Claude Code config) and syncs it to all your agents with one command.

┌──────────────┐
│  Claude Code │  Source of Truth
│  .cursor.json│  ─── MCP Servers
│  .mcp.json   │  ─── Rules (CLAUDE.md)
│  CLAUDE.md   │
└──────┬───────┘
       │  agentsync sync
       ├──────────────────┐─────────────────┐
       ▼                  ▼                 ▼
┌──────────────┐  ┌──────────────┐  ┌──────────────┐
│    Cursor    │  │    Codex     │  │  Antigravity │
│  mcp.json   │  │ config.toml  │  │mcp_config.json│
│ project.mdc │  │  AGENTS.md   │  │              │
└──────────────┘  └──────────────┘  └──────────────┘

Installation

pip install agentsync-cli     # pip
pipx install agentsync-cli    # pipx (recommended for CLI tools)
uvx agentsync-cli             # uv (run without installing)

Quick Start

agentsync init       # Create agentsync.yaml config
agentsync sync       # Sync to all agents
agentsync validate   # Verify everything is correct

Features

• MCP server sync — JSON ↔ TOML automatic conversion
• Rules sync — Markdown → filtered Markdown / MDC with frontmatter
• Case-insensitive deduplication — han