Trabuco MCP Server

Production Java Maven scaffolder (CLI + Claude Code plugin) for AI coding agents

Local serverstdioGo

What is the Trabuco MCP server?

Most developer tooling work still happens through a UI a human drives. Trabuco MCP server moves it into the conversation instead. Production Java Maven scaffolder (CLI + Claude Code plugin) for AI coding agents.

The short version

  • Multi-module Maven — — clean compile-time boundaries between Model, SQLDatastore/NoSQLDatastore, Shared, API, Worker, EventConsumer, AIAgent
  • Spring Boot + Java — — Spring Data JDBC (no JPA), Flyway migrations, virtual threads on by default, Testcontainers for real integration tests
  • Production observability — — RFC 7807 Problem Details, OpenTelemetry auto-instrumentation, Prometheus metrics, correlation IDs, health probes
  • AI Agent module — — Spring AI with tools, LLM guardrails, MCP server, A2A protocol, multi-agent orchestration, knowledge base, webhooks. The OIDC chain coexists with the legacy ApiKeyAuthFilter (governed by an independent property) for incremental migration
  • AI collaboration layer — — .ai/prompts/ task guides, JAVA_CODE_QUALITY.md spec, per-agent rule files for Claude Code / Codex / Cursor / GitHub Copilot
  • Migration of existing repos — — trabuco migrate runs a 14-phase orchestrated flow with per-phase approval gates and atomic rollback

Getting it running

Installation goes through your MCP client rather than a global install: point it at trabuco-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

The tools it exposes

The server publishes 2 tools. What each one is for:

  • Multi — module Maven** — clean compile-time boundaries between Model, SQLDatastore/NoSQLDatastore, Shared, API, Worker, EventConsumer, AIAgent
  • MavenDocker (for Testcontainers and local development)

What it needs from you

  • Java (Trabuco auto-detects installed versions) - Maven - Docker (for Testcontainers and local development)

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Trabuco's toolset — Multi, Maven — is a fair guide to whether it matches your workflow. It is maintained by arianlopezc; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Trabuco's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
Multimodule Maven** — clean compile-time boundaries between Model, SQLDatastore/NoSQLDatastore, Shared, API, Worker, EventConsumer, AIAgent.
Maven**Docker** (for Testcontainers and local development)

How to install the Trabuco MCP server

{
  "mcpServers": {
    "trabuco": {
      "command": "npx",
      "args": ["-y", "trabuco-mcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Java (Trabuco auto-detects installed versions) - Maven - Docker (for Testcontainers and local development)

Example prompts to try

  • Use Trabuco to Multi.
  • Use Trabuco to Maven.

Frequently asked questions

It connects Trabuco to MCP-compatible AI assistants such as Claude and Cursor, exposing 2 tools (Multi, Maven) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Trabuco directly.