MCP Manager
A cross-platform, single-binary manager for Model Context Protocol (MCP) servers, built with Go and a reactive HTMX web interface.
What is MCP Manager?
MCP Manager is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to cross-platform, single-binary manager for model context protocol (mcp) servers, built with go and a reactive htmx web interface.
A cross-platform, single-binary manager for Model Context Protocol (MCP) servers, built with Go and a reactive HTMX web interface.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A cross-platform, single-binary manager for Model Context Pr
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx managerConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Manager
MCP Server Manager is a cross-platform single-binary tool written in Go that solves the pain of manually editing multiple JSON configuration files when managing MCP servers across different AI clients. It provides a reactive HTMX web interface at http://localhost:6543, reads a single YAML configuration file, and automatically syncs MCP server settings to Claude Code, Gemini CLI, and other supported clients — with real-time validation and dark/light theme support.
Prerequisites
- One of: Debian/Ubuntu Linux, macOS, or Windows (pre-built binaries available for all)
- At least one MCP client installed (Claude Code, Gemini CLI, etc.)
- wget or curl for downloading the release binary (or Go 1.21+ to build from source)
Download and install the binary
Download the pre-built binary for your platform from GitHub Releases. On Debian/Ubuntu you can install the .deb package; on other platforms extract the archive.
# Debian / Ubuntu — install as a system service
wget https://github.com/vlazic/mcp-server-manager/releases/latest/download/mcp-server-manager_Linux_x86_64.deb
sudo dpkg -i mcp-server-manager_Linux_x86_64.deb
systemctl --user enable --now mcp-server-manager
# Linux (tarball) or macOS
wget https://github.com/vlazic/mcp-server-manager/releases/latest/download/mcp-server-manager_Linux_x86_64.tar.gz
tar -xzf mcp-server-manager_Linux_x86_64.tar.gz
chmod +x mcp-server-manager
./mcp-server-managerBuild from source (optional)
If you prefer to build from source, clone the repository and use make.
git clone https://github.com/vlazic/mcp-server-manager.git
cd mcp-server-manager
# Build only
make build
# Build, install, and start as system service
make setupOpen the web interface
Once running, open your browser to the MCP Server Manager interface. It auto-detects your system theme and provides real-time config validation.
open http://localhost:6543
# or
xdg-open http://localhost:6543 # LinuxAdd an MCP server via the web UI
Click 'Add New Server' in the web interface, choose from built-in examples or enter your own server configuration, then submit. Changes are automatically applied to all registered client config files.
# The UI supports both STDIO and HTTP transport types
# Example: add a filesystem server via the form
# Name: filesystem
# Command: npx
# Args: @modelcontextprotocol/server-filesystem /path/to/dirOr edit the YAML config file directly
Advanced users can edit the central YAML configuration file at ~/.config/mcp-server-manager/config.yaml. Changes take effect after restarting the service.
# ~/.config/mcp-server-manager/config.yaml
server_port: 6543
mcpServers:
filesystem:
command: "npx"
args: ["@modelcontextprotocol/server-filesystem", "/path/to/your/directory"]
env:
NODE_ENV: "production"
context7:
type: "http"
url: "https://mcp.context7.com/mcp"MCP Manager Examples
Client configuration
MCP Server Manager manages client configs for you. Here is the central YAML config it reads — you do not edit individual client JSON files manually.
server_port: 6543
mcpServers:
filesystem:
command: "npx"
args: ["@modelcontextprotocol/server-filesystem", "/home/user/projects"]
env:
NODE_ENV: "production"
context7:
type: "http"
url: "https://mcp.context7.com/mcp"
github:
command: "npx"
args: ["@modelcontextprotocol/server-github"]
env:
GITHUB_PERSONAL_ACCESS_TOKEN: "ghp_yourtoken"Prompts to try
MCP Server Manager is a GUI/CLI management tool rather than an MCP server itself. Use these workflows after setup.
- Open http://localhost:6543 and click 'Add New Server' to add a new MCP server to all clients at once
- Use the web UI toggle to enable or disable a server for a specific AI client without editing JSON
- Specify '--config /path/to/config.yaml' to use a custom config location for team-shared configs
- Check real-time validation feedback in the UI when pasting a new server configurationTroubleshooting MCP Manager
Web interface not accessible at localhost:6543
Verify the mcp-server-manager process is running with 'systemctl --user status mcp-server-manager' (Linux service) or by checking for the process directly. If port 6543 is in use, change server_port in config.yaml and restart.
Changes in the web UI are not reflected in Claude Code or Gemini CLI
Ensure MCP Server Manager knows the correct paths to your client configuration files. Check ~/.config/mcp-server-manager/config.yaml for client path settings and verify the paths exist. You may need to restart the AI client after the sync.
Config file not found on first run
On first run, MCP Server Manager auto-creates a default config at ~/.config/mcp-server-manager/config.yaml. If it does not appear, run the binary manually from a terminal to see any startup errors, and ensure the ~/.config directory is writable.
Frequently Asked Questions about MCP Manager
What is MCP Manager?
MCP Manager is a Model Context Protocol (MCP) server that cross-platform, single-binary manager for model context protocol (mcp) servers, built with go and a reactive htmx web interface. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Manager?
Follow the installation instructions on the MCP Manager GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP Manager?
MCP Manager works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Manager free to use?
Yes, MCP Manager is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
MCP Manager Alternatives — Similar Developer Tools Servers
Looking for alternatives to MCP Manager? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
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.
Set Up MCP Manager in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MCP Manager?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.