interop
Interop CLI: Go command-line tool for efficient project management and command execution across your development workspace.
claude mcp add --transport stdio yigitozgumus-interop interop mcp server domain1
How to use
Interop provides a unified command-line interface to manage multiple projects and expose their commands to AI assistants via MCP servers. The tool supports dynamic command loading, project validation, and remote configuration integration, making it easier to organize numerous domains of work under a single orchestration layer. In practice, you can define projects and commands locally in TOML files, load commands from multiple directories, and assign specific commands to different MCP servers so AI assistants can discover context-aware actions for each domain. Use interop projects to list and inspect your configured projects, run commands with project context, and leverage the remote configuration system to fetch shared command definitions from Git repositories. The two MCP servers domain1 and domain2 act as separate exposure points for AI-assisted interactions, each bound to its own port as defined in the configuration, enabling fine-grained control over which commands are available to AI agents in each domain. To execute a command, invoke the Interop CLI with the appropriate run or config commands, and the engine will resolve the command across the configured project and domain contexts.
How to install
Prerequisites:
- Go 1.18+ installed on your system
- A supported shell (bash/zsh on Linux/macOS, PowerShell on Windows)
- Git installed for remote configuration features (optional but recommended)
Install from source or via prebuilt binaries:
Option 1: Build from source
-
Clone the repository git clone https://github.com/yigitozgumus/interop.git cd interop
-
Build the CLI binary go build -o interop ./cmd/cli
-
Move the binary to a directory in your PATH (optional) mv interop /usr/local/bin/
Option 2: Install via Homebrew (macOS/Linux)
- Add the formula and install brew install yigitozgumus/formulae/interop
Configuration steps (initial):
- Create the config directory if it doesn't exist: mkdir -p ~/.config/interop
- Create an initial settings.toml or use interop edit to configure: interop edit
Note: The Interop configuration relies on a TOML file at ~/.config/interop/settings.toml which defines MCP servers, projects, commands, and remote configuration settings. After building or installing, run interop to begin managing your projects and exposing commands to MCP servers.
Additional notes
Tips and common considerations:
- MCP servers domain1 and domain2 are defined to expose domain-specific commands via the Interop MCP interface. Each server has its own port as configured in your settings.toml; ensure those ports are open in your environment.
- The TOML configuration supports precedence rules: main settings.toml takes priority, followed by files in command_dirs directories in alphabetical order, then the files within those directories. This makes it safe to override shared configurations locally.
- If you enable remote configuration, you can fetch and merge remote command definitions while preserving local overrides. Conflict resolution favors local configurations.
- For AI integration, make sure the Interop process has access to the necessary environment and authentication if remote repositories require SSH keys or tokens.
- Use the built-in commands like interop projects to inspect current projects, and interop run <command> to execute a given command within the appropriate project context. Ensure your command definitions include correct mcp assignments to ensure they appear under the intended MCP server.
Related MCP Servers
ophis
Transform any Cobra CLI into an MCP server
workflowy
Powerful CLI and MCP server for WorkFlowy: reports, search/replace, backup support, and AI integration (Claude, LLMs)
homebutler
🏠 Manage your homelab from chat. Single binary, zero dependencies.
devir
Dev Runner CLI - Terminal UI for managing multiple dev services with colored logs, filtering, and MCP integration for Claude Code
shipyard-cli
The Shipyard CLI and MCP server enable you to manage ephemeral environments from your terminal or from your AI agent.
backlog
Help coding agents and developers to keep track of a project's backlog by storing tasks as markdown in git.