Skip to main content
Glama

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

fugu_orchestrate

Antigravity CLI (agy)

Fugu-style single entry point: fast routing or ultra workflow with subtasks, model_id, access_list, shared memory, and synthesis

consult_model

Antigravity CLI (agy)

Ask one external model for a second opinion

compare_models

Antigravity CLI (agy)

Ask 2-4 models in parallel and synthesize agreement/disagreement

adversarial_check

Antigravity CLI (agy)

Ask a model to attack a proposal, plan, or implementation idea

review_workspace

OpenAI Codex CLI

Run scoped code review on uncommitted changes, a base branch, or a commit

security_audit

OpenAI Codex CLI

Run a security-focused Codex review prompt

run_antigravity

Antigravity CLI (agy)

Compatibility wrapper with safe subcommands only

run_codex

OpenAI Codex CLI

Compatibility wrapper for codex review only

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

Install

git clone https://github.com/Marcelo-Henry/mcp-cli-tools.git
cd mcp-cli-tools
npm install
npm run build

Configure 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_orchestrate is 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:

  • prompt e flags são mutuamente exclusivos e agora são validados pelo MCP.

  • Use cwd quando o comando depender do contexto de um repositório específico.

  • action agora aceita apenas review.

  • flags aceita apenas --uncommitted, --base, --commit, --title e --strict-config.

Error handling

Os tools retornam:

  • comando executado

  • cwd usado

  • exit_code

  • duration_ms

  • stdout e stderr

  • structuredContent com 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

gemini-3.5-flash

Fast exploration, brainstorming (default)

gemini-3.1-pro

Deep analysis, architecture, large context

gpt-oss-120b

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 tools
adversarial_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

    B3.4/5.0

    Scored across 8 tools

    Disambiguation2/5

    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.

    Naming Consistency3/5

    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.

    Tool Count5/5

    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.

    Completeness4/5

    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

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      An 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.
      1
      148
      MIT
    • A
      license
      A
      quality
      A
      maintenance
      An 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.
      33
      1,045 PyPI
      34
      MIT