Playground AI MCP Server for Mastra AI 10 tools — connect in under 2 minutes
Mastra AI is a TypeScript-native agent framework built for modern web stacks. Connect Playground AI through Vinkius and Mastra agents discover all tools automatically. type-safe, streaming-ready, and deployable anywhere Node.js runs.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import { Agent } from "@mastra/core/agent";
import { createMCPClient } from "@mastra/mcp";
import { openai } from "@ai-sdk/openai";
async function main() {
// Your Vinkius token. get it at cloud.vinkius.com
const mcpClient = await createMCPClient({
servers: {
"playground-ai": {
url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
},
},
});
const tools = await mcpClient.getTools();
const agent = new Agent({
name: "Playground AI Agent",
instructions:
"You help users interact with Playground AI " +
"using 10 tools.",
model: openai("gpt-4o"),
tools,
});
const result = await agent.generate(
"What can I do with Playground AI?"
);
console.log(result.text);
}
main();
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Playground AI MCP Server
Connect your AI agent directly to the Playground AI compute clusters. Eliminate manual interface dragging by instructing your LLM (Claude, Cursor) to natively generate, radically outpaint, or surgically inpaint high-resolution visual components using the Playground v3 pipeline.
Mastra's agent abstraction provides a clean separation between LLM logic and Playground AI tool infrastructure. Connect 10 tools through Vinkius and use Mastra's built-in workflow engine to chain tool calls with conditional logic, retries, and parallel execution. deployable to any Node.js host in one command.
What you can do
- Direct Image Generation — Generate pristine assets instantly. Use the
generate_imagetool explicitly defining prompt nuances and tensor geometries (like 1024x1024). - ControlNet & Transformations — Substantially alter base images. Tell the agent to use
controlnet(depth/canny) or apply rawtransform_imageoverrides mutating your sketches into polished renders. - Precision Editing — Execute flawless structural edits. Instruct the AI to seamlessly
remove_backgroundand isolate elements, or useinpaint_imageoverlaying explicit masks. - Upscaling & Outpainting — Scale blurry inputs intelligently up to 4x, or instruct the diffusion model to geometrically expand boundary borders utilizing
outpaint_image.
The Playground AI MCP Server exposes 10 tools through the Vinkius. Connect it to Mastra AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Playground AI to Mastra AI via MCP
Follow these steps to integrate the Playground AI MCP Server with Mastra AI.
Install dependencies
Run npm install @mastra/core @mastra/mcp @ai-sdk/openai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.ts and run with npx tsx agent.ts
Explore tools
Mastra discovers 10 tools from Playground AI via MCP
Why Use Mastra AI with the Playground AI MCP Server
Mastra AI provides unique advantages when paired with Playground AI through the Model Context Protocol.
Mastra's agent abstraction provides a clean separation between LLM logic and tool infrastructure. add Playground AI without touching business code
Built-in workflow engine chains MCP tool calls with conditional logic, retries, and parallel execution for complex automation
TypeScript-native: full type inference for every Playground AI tool response with IDE autocomplete and compile-time checks
One-command deployment to any Node.js host. Vercel, Railway, Fly.io, or your own infrastructure
Playground AI + Mastra AI Use Cases
Practical scenarios where Mastra AI combined with the Playground AI MCP Server delivers measurable value.
Automated workflows: build multi-step agents that query Playground AI, process results, and trigger downstream actions in a typed pipeline
SaaS integrations: embed Playground AI as a first-class tool in your product's AI features with Mastra's clean agent API
Background jobs: schedule Mastra agents to query Playground AI on a cron and store results in your database automatically
Multi-agent systems: create specialist agents that collaborate using Playground AI tools alongside other MCP servers
Playground AI MCP Tools for Mastra AI (10)
These 10 tools become available when you connect Playground AI to Mastra AI via MCP:
generate_image
Triggers immediate billing execution per inference step. Generate images from a text prompt using Playground AI. Playground offers multiple AI models including Playground v3 and SDXL variants for creative image generation. Instructions: Pass prompt, model name, width, height (multiples of 64)
generate_with_controlnet
Generate images with ControlNet guidance using Playground AI. Control types: canny, depth, pose, scribble. Instructions: Pass prompt, reference image URL, control type
get_generation
Get details of a Playground AI generation by ID. Returns images, prompt, model, and metadata
inpaint_image
Inpaint specific areas of an image using Playground AI. Uses a mask to define regions. Instructions: Pass prompt, image URL, and mask image URL (white = edit area)
list_generations
List recent generations on Playground AI. Returns generation IDs, prompts, and timestamps
list_models
List available models on Playground AI. Returns model names, descriptions, and capabilities
outpaint_image
Extend an image beyond its borders using Playground AI. AI generates new content in the specified direction. Instructions: Pass prompt, image URL, direction (up/down/left/right)
remove_background
Remove the background from an image using Playground AI. Returns transparent PNG. Instructions: Pass public image URL
transform_image
Transform an existing image with a text prompt using Playground AI. Strength controls how much the image changes (0-1). Instructions: Pass prompt, public image URL, and strength
upscale_image
Upscale an image using Playground AI. Enhances resolution and detail. Instructions: Pass image URL and scale factor (2 or 4)
Example Prompts for Playground AI in Mastra AI
Ready-to-use prompts you can give your Mastra AI agent to start working with Playground AI immediately.
"Generate a 1024x1024 image of a cyberpunk coffee cup in neon lighting."
"Upscale this image to 4x its size `https://example.com/small_icon.png`."
"Remove the background from the image at `https://example.com/person.jpg`."
Troubleshooting Playground AI MCP Server with Mastra AI
Common issues when connecting Playground AI to Mastra AI through the Vinkius, and how to resolve them.
createMCPClient not exported
npm install @mastra/mcpPlayground AI + Mastra AI FAQ
Common questions about integrating Playground AI MCP Server with Mastra AI.
How does Mastra AI connect to MCP servers?
MCPClient with the server URL and pass it to your agent. Mastra discovers all tools and makes them available with full TypeScript types.Can Mastra agents use tools from multiple servers?
Does Mastra support workflow orchestration?
Connect Playground AI with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Playground AI to Mastra AI
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.