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 "Deploy 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-tools Review 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.) safe 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, compare answers, ask for adversarial review, and run scoped code reviews without leaving the editor.
What it does
Tool | Backend | Capability |
| Antigravity CLI ( | Fugu-style single entry point: fast routing or ultra workflow with subtasks, |
| Antigravity CLI ( | Ask one external model for a second opinion |
| Antigravity CLI ( | Ask 2-4 models in parallel and synthesize agreement/disagreement |
| Antigravity CLI ( | Ask a model to attack a proposal, plan, or implementation idea |
| OpenAI Codex CLI | Run scoped code review on uncommitted changes, a base branch, or a commit |
| OpenAI Codex CLI | Run a security-focused Codex review prompt |
| Antigravity CLI ( | Compatibility wrapper with safe subcommands only |
| OpenAI Codex CLI | Compatibility wrapper for |
Your AI agent gains the ability to:
Get a second opinion from a different model family
Use a single Fugu-style tool that hides routing, decomposition, worker calls, and final synthesis
Compare multiple external answers in one tool call
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
Receive structured metadata for each call: command, cwd, exit code, timeout, duration, stdout, stderr
Related MCP server: agent-intern
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
fugu_orchestrate
Use this as the main entry point when you want behavior closest to Fugu/Fugu-Ultra.
Fast mode selects one worker for lower latency:
fugu_orchestrate(
task: "Explain this TypeScript error and suggest the smallest fix",
mode: "fast",
effort: "standard",
cwd: "/path/to/repo"
)Ultra mode builds and executes a workflow with model_id, subtasks, access_list, critique, and synthesis:
fugu_orchestrate(
task: "Create a local task dashboard from scratch with persistence, tests, and a polished UI",
mode: "ultra",
effort: "max",
sharedMemoryKey: "taskpulse",
cwd: "/path/to/repo"
)Restrict the worker pool when privacy, cost, or compliance matters:
fugu_orchestrate(
task: "Analyze this architecture",
mode: "ultra",
excludeModels: ["gpt-oss-120b"]
)
fugu_orchestrateis a local deterministic orchestration layer inspired by the public Fugu/Fugu-Ultra workflow shape. It is not Sakana's learned orchestrator model.
consult_model
Ask one external model:
consult_model(prompt: "Analyze this architecture", model: "gemini-3.1-pro", cwd: "/path/to/repo")compare_models
Ask multiple models in parallel:
compare_models(
prompt: "Which migration strategy is safest for this repo?",
models: ["gemini-3.5-flash", "gemini-3.1-pro"]
)adversarial_check
Ask an external model to find flaws in a proposal:
adversarial_check(
proposal: "Move all orchestration policy into CLAUDE.md",
context: "MCP server for Claude Code + GPT/Gemini collaboration"
)review_workspace
Review uncommitted changes:
review_workspace(scope: "uncommitted", cwd: "/path/to/repo")Review against a branch:
review_workspace(scope: "base", base: "main", cwd: "/path/to/repo")Review a commit:
review_workspace(scope: "commit", commit: "abc123", cwd: "/path/to/repo")security_audit
Run a security-focused review:
security_audit(instructions: "Focus on command execution and path traversal", cwd: "/path/to/repo")Compatibility tools
run_antigravity and run_codex remain available for existing Claude rules, but they are intentionally narrower now.
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 safe subcommands:
run_antigravity(subcommand: "help")
run_antigravity(subcommand: "changelog")Allowed subcommands are models, help, and changelog. Plugin/install/update operations are blocked by design.
run_codex
Review uncommitted changes:
run_codex(action: "review", flags: ["--uncommitted"], cwd: "/path/to/repo")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"], cwd: "/path/to/repo")Use a specific model:
run_codex(action: "review", prompt: "Audit this code", model: "gpt-5", cwd: "/path/to/repo")Notes:
prompteflagssão mutuamente exclusivos e agora são validados pelo MCP.Use
cwdquando o comando depender do contexto de um repositório específico.
actionagora aceita apenasreview.
flagsaceita apenas--uncommitted,--base,--commit,--titlee--strict-config.
Error handling
Os tools retornam:
comando executado
cwdusadoexit_codeduration_msstdoutestderrstructuredContentcom metadata da chamada
Se o processo sair com código diferente de zero, receber sinal ou estourar timeout, o resultado é marcado como erro no protocolo MCP.
Available Models
Via Antigravity
Model | Best for |
| Fast exploration, brainstorming (default) |
| Deep analysis, architecture, large context |
| Independent perspective, diverse opinion |
Via Codex
Codex models depend on your local Codex CLI configuration. Pass the model explicitly when needed:
review_workspace(scope: "uncommitted", model: "gpt-5", cwd: "/path/to/repo")
security_audit(model: "gpt-5", cwd: "/path/to/repo")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
Available Tools
8 toolsadversarial_checkA
Pede a um modelo externo para atacar uma proposta, plano ou solucao e apontar falhas concretas.
Inputs: proposal (required), cwd, model, context, +1 more.
compare_modelsA
Envia a mesma pergunta para 2-4 modelos Antigravity em paralelo para second opinion, consenso ou divergencia.
Inputs: prompt (required), cwd, models, timeoutMs.
consult_modelA
Consulta um modelo externo via Antigravity em modo nao interativo e retorna texto bruto mais metadata estruturada.
Inputs: prompt (required), cwd, model, timeoutMs.
fugu_orchestrateB
Executa uma orquestracao local estilo Fugu: modo fast seleciona um worker; modo ultra cria workflow com model_id, subtasks, access_list, memoria compartilhada e sintese.
Inputs: task (required), cwd, mode, effort, +5 more.
review_workspaceA
Executa codex review em um escopo seguro: alteracoes uncommitted, diff contra base ou commit especifico.
Inputs: cwd, base, model, scope, +3 more.
run_antigravityA
Compatibilidade: executa apenas consultas seguras da Antigravity CLI. Para prompts, prefira consult_model ou compare_models.
Inputs: cwd, args, model, timeoutMs, +2 more.
run_codexA
Compatibilidade: executa apenas codex review com flags seguras. Para workflows novos, prefira review_workspace ou security_audit.
Inputs: cwd, flags, model, action, +2 more.
security_auditC
Executa uma auditoria de seguranca via codex review com prompt especializado.
Inputs: cwd, model, timeoutMs, instructions.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Several tools overlap in functionality: run_antigravity and consult_model both query Antigravity, while run_codex overlaps with review_workspace and security_audit. The descriptions explicitly say to prefer other tools for new workflows, creating confusing boundaries.
Most tools follow verb_noun (run_antigravity, consult_model, compare_models, review_workspace), but security_audit, adversarial_check, and fugu_orchestrate break the pattern with noun_noun, adjective_noun, and noun_verb structures. All are lowercase snake_case, so it remains readable.
With 8 tools, the set is well-scoped for an AI CLI toolkit covering model queries, comparisons, reviews, audits, and orchestration. Each tool addresses a distinct workflow area, and the count is within the ideal range.
The toolkit covers core workflows: model consultation, comparison, adversarial checking, code review, security audit, and orchestration. Minor gaps exist, such as no tool for listing available models or directly executing code, but the primary surface is solid.
Maintenance
Related MCP Connectors
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
An MCP server that gives your AI access to the source code and docs of all public github repos
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
Related MCP Servers
- AlicenseAqualityBmaintenanceAn MCP server that lets Claude Code consult stronger AI models (o3, Gemini 2.5 Pro, DeepSeek Reasoner) when you need deeper analysis on complex problems.1148MIT
- AlicenseAqualityAmaintenanceAn MCP server that bridges Claude Code with Antigravity CLI using a Swarm Agent architecture to optimize local development workflows and minimize LLM token costs. Includes a web UI for monitoring agent workflows.331,045 PyPI34MIT
- AlicenseNot gradedqualityDmaintenanceA multi-agent MCP server that enables AI coding agents (Claude Code, Codex CLI, Gemini CLI) to communicate with each other.MIT

MCP Rubber Duckofficial
AlicenseAqualityDmaintenanceAn MCP server that bridges multiple LLMs (OpenAI-compatible APIs and CLI coding agents) for collaborative debugging and diverse AI perspectives.126MIT