Spring AI Playground

Spring AI Playground is a cross-platform desktop app for building, testing, and exposing executable MCP tools for MCP-compatible hosts and clients.

The desktop app is the recommended default experience, but Docker and local source execution are still supported when you want a server-style deployment or a development workflow.

Unlike many playgrounds that stop at prompt testing, this project connects AI conversations to real actions:

build JavaScript tools directly in the app
expose them immediately through MCP without restart or redeploy
validate retrieval pipelines against your own documents
run agentic chat that combines tool use and grounded context

Agentic Chat Demo
Tool-enabled agentic AI built with Spring AI and MCP

Quick Start

The recommended default is the desktop app distributed from GitHub Releases.

1. Download the Desktop App

Choose the installer for your platform from the latest release:

Or browse all available assets on the Releases page.

2. Install and Launch

Install the package the same way you would for a normal desktop application, then launch Spring AI Playground from your applications menu.

The desktop app bundles the backend runtime together with a launcher that provides provider starter templates, YAML override editing, environment-variable based secret handling, and one-click launch.

For macOS-specific install notes, Gatekeeper guidance, and quarantine troubleshooting, see Getting Started.

3. Start with the Built-in Desktop Runtime

The desktop build is intended to be the easiest way to get started without setting up Docker or running the server manually.

4. Optional: Use Docker Instead

If you prefer container-based startup, run:

docker run -d -p 8282:8282 --name spring-ai-playground \
  -e SPRING_AI_OLLAMA_BASE_URL=http://host.docker.internal:11434 \
  -v spring-ai-playground:/home \
  --restart unless-stopped \
  ghcr.io/spring-ai-community/spring-ai-playground:latest

Then open http://localhost:8282.

What You Can Do

AI Models: switch between Ollama, OpenAI, and OpenAI-compatible runtime paths.
Tool Studio: build low-code tools in JavaScript and expose them instantly through MCP.
MCP Server: inspect external MCP servers and consume built-in MCP tools.
RAG: upload content, chunk it, embed it, index it, and validate retrieval quality.
Agentic Chat: combine grounded context and tool-enabled reasoning in one interaction flow.

Why This Project Exists

Spring AI Playground is intentionally positioned as a tool-first environment for building, validating, and operationalizing MCP tools in a practical workflow.

Its current focus is:

providing a UI-driven environment for building, testing, and validating MCP tools in a practical workflow
testing tool execution flows, environment-backed tool configuration, and RAG integration in one place
making tools easier to inspect, easier to test, and easier to operationalize before they are reused elsewhere
promoting validated tools into standalone, deployment-ready MCP servers that can be reused by multiple MCP-compatible hosts and clients

It is intentionally opinionated and scope-limited in its current stage. The goal is a stable, reproducible platform for practical MCP tool work rather than a feature-complete agent orchestration product.

Documentation Flow

Getting Started: install the desktop app first, configure models, and understand alternative runtimes
Features: understand the architecture and the main product areas
Tutorials: follow real workflows for tools, MCP, vector search, and agentic chat