
Ai Cli Mcp
This server wraps Claude Code, Codex, Gemini CLI, Forge, and OpenCode so you can orchestrate multiple AI agents from within Claude Desktop or other MCP clients. It exposes run, wait, kill, and result tools that launch background processes with permissions bypassed, return immediately with a PID, and let you poll or block until completion. The real win is parallel execution: kick off three refactoring tasks with different models, move on to something else, then collect results when they finish. It also supports session IDs for context reuse across runs, which saves prompt caching costs when you're iterating on large codebases. You'll need each CLI installed and authenticated locally before the server can invoke them non-interactively.
- GitHub stars
- 27
- tools
- 8
- transport
- STDIO
- last updated
- Sep 13, 2026
Tools
8 toolsPublic tool metadata for what this MCP can expose to an agent.
runExecutes a prompt using Claude CLI, Codex CLI, Antigravity CLI (Gemini), OpenCode, Grok, or Pi. The appropriate CLI is automatically selected based on the model name.
Executes a prompt using Claude CLI, Codex CLI, Antigravity CLI (Gemini), OpenCode, Grok, or Pi. The appropriate CLI is automatically selected based on the model name.
No parameter schema in public metadata yet.
waitWaits for multiple AI agent processes to complete and returns their combined results. Blocks until all specified PIDs finish or a timeout occurs.
Waits for multiple AI agent processes to complete and returns their combined results. Blocks until all specified PIDs finish or a timeout occurs.
No parameter schema in public metadata yet.
peekStarts a one-shot short observation window for running child agents and returns structured events observed during that specific call.
Starts a one-shot short observation window for running child agents and returns structured events observed during that specific call.
No parameter schema in public metadata yet.
list_processesLists all running and completed AI agent processes with their status, PID, and basic info.
Lists all running and completed AI agent processes with their status, PID, and basic info.
No parameter schema in public metadata yet.
doctorChecks supported AI CLI binary availability and path resolution from MCP clients.
Checks supported AI CLI binary availability and path resolution from MCP clients.
No parameter schema in public metadata yet.
modelsLists supported model names and aliases, including models discovered by running pi --list-models and opencode models.
Lists supported model names and aliases, including models discovered by running pi --list-models and opencode models.
No parameter schema in public metadata yet.
get_resultGets the current output and status of an AI agent process by PID.
Gets the current output and status of an AI agent process by PID.
No parameter schema in public metadata yet.
kill_processTerminates a running AI agent process by PID.
Terminates a running AI agent process by PID.
No parameter schema in public metadata yet.
Sponsors
Readme
AI CLI MCP Server
📦 Package Migration Notice: This package was formerly
@mkxultra/claude-code-mcpand has been renamed toai-cli-mcpto reflect its expanded support for multiple AI CLI tools.
An MCP (Model Context Protocol) server that allows running AI CLI tools (Claude, Codex, Gemini, OpenCode, Grok, and Pi) in background processes with automatic permission handling.
Did you notice that Cursor sometimes struggles with complex, multi-step edits or operations? This server, with its powerful unified run tool, enables multiple AI agents to handle your coding tasks more effectively.
Demo
Overview
This MCP server provides tools that can be used by LLMs to interact with AI CLI tools. When integrated with MCP clients, it allows LLMs to:
Details
- Repository
- github.com/mkxultra/ai-cli-mcp
- Category
- AI & LLM Tools
- Package
ai-cli-mcp- Transport
- STDIO
- Registry
- MCP registry, active