Happy slice of mcp pizzaMCP.pizza

ai-cli-mcp

MCP.Pizza Chef: mkXultra

This server lets you run powerful AI coding assistants like Claude, Codex, Gemini, and others as background tools accessible from apps like Cursor and Windsurf. After installing and configuring these AI command-line tools on your computer, you can manage multiple AI tasks simultaneously, such as code refactoring, testing, and documentation. It requires some initial setup, like running the AI tools once manually to accept permissions, but then works seamlessly to speed up your coding workflows.

Coding
Other

Use This MCP server To

Run multiple AI coding agents in parallel Refactor code using Claude or Codex models Generate unit tests automatically Update project documentation with AI help Reuse project context across tasks to save time Manage AI tasks from Cursor or Windsurf apps Switch between different AI models easily

README

AI CLI MCP Server

npm package View changelog

🇯🇵 日本語のREADMEはこちら

📦 Package Migration Notice: This package was formerly @mkxultra/claude-code-mcp and has been renamed to ai-cli-mcp to reflect its expanded support for multiple AI CLI tools.

An MCP (Model Context Protocol) server that allows running AI CLI tools (Claude, Codex, Gemini, Forge, and OpenCode) 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

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:

  • Run Claude CLI with all permissions bypassed (using --dangerously-skip-permissions)
  • Execute Codex CLI with approvals and sandbox bypassed (using --dangerously-bypass-approvals-and-sandbox)
  • Execute Gemini CLI with automatic approval mode (using -y)
  • Execute Forge CLI in non-interactive mode (using forge -C <workFolder> -p <prompt>)
  • Execute OpenCode in non-interactive JSON mode (using opencode run --format json --dir <workFolder> <prompt>)
  • Support multiple AI models: Claude (sonnet, sonnet[1m], opus, opusplan, fable, haiku), Codex (gpt-5.4, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna, gpt-5.5, gpt-5.4-mini, gpt-5.3-codex, gpt-5.3-codex-spark, gpt-5.2), Gemini (gemini-2.5-pro, gemini-2.5-flash, gemini-3.1-pro-preview, gemini-3-pro-preview, gemini-3-flash-preview), Forge (forge), and OpenCode (opencode plus explicit oc-<provider/model> wrappers such as oc-openai/gpt-5.4)
  • Manage background processes with PID tracking
  • Parse and return structured outputs from both tools

Usage Example (Advanced Parallel Processing)

You can instruct your main agent to run multiple tasks in parallel like this:

Launch agents for the following 3 tasks using acm mcp run:

  1. Refactor src/backend code using sonnet
  2. Create unit tests for src/frontend using gpt-5.3-codex
  3. Update docs in docs/ using gemini-2.5-pro

While they run, please update the TODO list. Once done, use the wait tool to wait for all completions and report the results together.

ai-cli-mcp FAQ

Can I use this to run multiple AI coding agents in the background?
Yes — it lets you run Claude, Codex, Gemini, and other AI CLI agents simultaneously from any MCP client like Cursor or Windsurf.
Can I use this to speed up complex coding tasks with AI?
Yes — it supports multitasking and lets your AI run multiple code edits or tests in parallel.
Which apps can I use this with?
It works with MCP-compatible clients such as Cursor and Windsurf.
Do I need to set up accounts or API keys?
You must install and configure the AI CLI tools (Claude, Codex, Gemini, etc.) locally and complete their initial login and setup.
How hard is it to set up?
Setup involves pasting a small config snippet and installing CLI tools, so it's moderate but does not require coding.
Do I need to run anything manually first?
Yes — for example, you must run Claude CLI once manually with special flags to accept terms before using it here.
Can I switch between different AI models?
Yes — it supports many models from Claude, Codex, Gemini, Forge, and OpenCode, letting you pick the best for your task.