mcp-cli-tools
Allows AI agents to run code reviews, security audits, and workspace-aware analysis using OpenAI Codex CLI models (e.g., GPT-5.5, GPT-5.4).
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-cli-toolsReview my uncommitted changes"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-cli-tools
MCP server that gives AI coding agents (Claude Code, Cursor, Cline, etc.) access to multiple AI models through Antigravity CLI and OpenAI Codex CLI.
Think of it as a local Fugu-style orchestrator — your AI agent can consult Gemini, GPT, and other models mid-conversation without leaving the editor.
What it does
Tool | Backend | Capability |
| Antigravity CLI ( | Query any model: Gemini 3.5 Flash, Gemini 3.1 Pro, Claude Sonnet/Opus, GPT-OSS 120B |
| OpenAI Codex CLI | Code review, security audit, workspace-aware analysis with GPT-5.5/5.4 |
Your AI agent gains the ability to:
Get a second opinion from a different model family
Run code reviews via Codex without leaving the conversation
Do adversarial verification (one model checks another's work)
Route by expertise — Gemini for analysis, GPT for code review
Related MCP server: MCP Coding Agents
Prerequisites
Antigravity CLI installed as
agyOpenAI Codex CLI installed as
codexNode.js 18+
Install
git clone https://github.com/Marcelo-Henry/mcp-cli-tools.git
cd mcp-cli-tools
npm install
npm run buildConfigure in Claude Code
Add to ~/.claude/settings.json under mcpServers:
{
"mcpServers": {
"cli-tools": {
"command": "node",
"args": ["/path/to/mcp-cli-tools/dist/index.js"]
}
}
}Usage
run_antigravity
Query any model available in Antigravity CLI:
run_antigravity(promptContext: "Analyze this architecture", model: "gemini-3.1-pro")List available models:
run_antigravity(subcommand: "models")Run subcommands:
run_antigravity(subcommand: "help")
run_antigravity(subcommand: "plugin", args: ["list"])run_codex
Review uncommitted changes:
run_codex(action: "review", flags: ["--uncommitted"])Review with a specific prompt:
run_codex(action: "review", prompt: "Focus on security vulnerabilities")Review against a branch:
run_codex(action: "review", flags: ["--base", "main"])Use a specific model:
run_codex(action: "review", prompt: "Audit this code", model: "gpt-5.5")Note:
promptandflags(--uncommitted,--base) are mutually exclusive in Codex CLI.
Available Models
Via Antigravity
Model | Best for |
| Fast exploration, brainstorming (default) |
| Deep analysis, architecture, large context |
| Independent perspective, diverse opinion |
Via Codex
Model | Best for |
| Deep review, security audit (default) |
| Fast review, general analysis |
Making your AI agent orchestrate automatically
Add orchestration rules to your global ~/.claude/CLAUDE.md to make Claude Code call these tools proactively. See ORCHESTRATION.md for a full guide with triggers and patterns.
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Marcelo-Henry/mcp-cli-tools'
If you have feedback or need assistance with the MCP directory API, please join our Discord server