MCP Sync

v1.0.0Developer Toolsstable

Sync MCP (Model Context Protocol) configurations across AI tools

mcp-syncmcpai-integration
Share:
45
Stars
0
Downloads
0
Weekly
0/5

What is MCP Sync?

MCP Sync is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to sync mcp (model context protocol) configurations across ai tools

Sync MCP (Model Context Protocol) configurations across AI tools

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Sync MCP (Model Context Protocol) configurations across AI t

Use Cases

Synchronize MCP configurations across AI tools
Share server settings between Claude, Cursor, and Windsurf
ztripez

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 15, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-sync

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCP Sync

MCP Sync is a command-line tool that synchronizes Model Context Protocol server configurations across multiple AI clients — Claude Desktop, Claude Code, Cline, Roo, VS Code, Cursor, and Continue. Instead of manually editing each client's JSON config when you add or update an MCP server, mcp-sync merges a single source of truth into all detected client configs automatically. Developers use it to keep their MCP server setup consistent across tools without repetitive copy-paste.

Prerequisites

  • Python 3.12 or higher
  • uv package manager (https://astral.sh/uv)
  • At least one MCP-compatible client installed (Claude Desktop, Cursor, VS Code, etc.)
  • The MCP server configurations you want to sync already defined or ready to add
1

Install mcp-sync

Install mcp-sync as a persistent uv tool so it is available globally.

uv tool install mcp-sync
2

Check the current sync status

Run status to see which MCP clients are detected on your system and what configurations are present.

mcp-sync status
3

Add an MCP server to sync

Use add-server to register a server that will be propagated to all supported clients. Specify the command, arguments, and any required environment variables.

mcp-sync add-server filesystem \
  --command npx \
  --args "-y,@modelcontextprotocol/server-filesystem,/home/user"
4

Preview the sync with dry-run

Run a dry-run to see exactly what changes will be made to each client's config file before committing.

mcp-sync sync --dry-run
5

Apply the sync

Run sync without the dry-run flag to write the configurations to all detected clients. Project-level configs take priority over global configs in the three-tier system.

mcp-sync sync
6

List all detected clients

Verify which clients were found and updated after syncing.

mcp-sync list-clients

MCP Sync Examples

Client configuration

Global mcp-sync config file at ~/.mcp-sync/global.json defining a server to sync to all clients.

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/home/user"],
      "env": {}
    }
  }
}

Prompts to try

Command patterns for common mcp-sync workflows.

- "mcp-sync status" — see all detected clients and their current configs
- "mcp-sync sync --dry-run" — preview what would change before applying
- "mcp-sync sync" — apply configs to all detected clients
- "mcp-sync list-clients" — list all supported clients found on the system
- "mcp-sync edit-client-definitions" — customize which clients are targeted
- "mcp-sync add-server myserver --command python --args '-m,myserver'" — add a new server

Troubleshooting MCP Sync

mcp-sync status shows no clients detected

mcp-sync auto-discovers clients by looking for their config files in standard locations. Ensure at least one client (Claude Desktop, Cursor, VS Code) is installed with its default config directory. You can also edit ~/.mcp-sync/client_definitions.json to add custom paths.

uvx mcp-sync command not found after installation

Ensure uv is installed and its bin directory is in your PATH. Run `which uv` to verify, then try `uv tool install mcp-sync` again and open a new terminal session.

Project config overrides global config unexpectedly

mcp-sync uses a three-tier priority system: project .mcp.json > global ~/.mcp-sync/global.json. If a project directory contains a .mcp.json, its servers take precedence. Run `mcp-sync sync --dry-run` to inspect the merge result before applying.

Frequently Asked Questions about MCP Sync

What is MCP Sync?

MCP Sync is a Model Context Protocol (MCP) server that sync mcp (model context protocol) configurations across ai tools It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCP Sync?

Follow the installation instructions on the MCP Sync GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with MCP Sync?

MCP Sync works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCP Sync free to use?

Yes, MCP Sync is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-sync": { "command": "npx", "args": ["-y", "mcp-sync"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use MCP Sync?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides