Agent Studio Starter

v1.0.0Coding Agentsstable

Stop building AI agents from scratch. Bootstrap starter Agent app with LangGraph, CopilotKit, and beautiful Generative UIs.

agentscopilotkitcopilotkitsdkdeep-agentsdocker
Share:
26
Stars
0
Downloads
0
Weekly
0/5

What is Agent Studio Starter?

Agent Studio Starter is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to stop building ai agents from scratch. bootstrap starter agent app with langgraph, copilotkit, and beautiful generative uis.

Stop building AI agents from scratch. Bootstrap starter Agent app with LangGraph, CopilotKit, and beautiful Generative UIs.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Stop building AI agents from scratch. Bootstrap starter Agen

Use Cases

Bootstrap agent apps
LangGraph integration
Generative UI
nsphung

Maintainer

LicenseApache-2.0
Languagejupyter notebook
Versionv1.0.0
UpdatedMay 2, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx agent-studio-starter

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Agent Studio Starter

Agent Studio Starter is a bootstrap template for building production-ready AI agent applications with LangGraph, CopilotKit, and generative UI components. It provides a pre-wired backend (Python/LangGraph) and frontend (Next.js/CopilotKit) so developers can skip agent scaffolding and focus on adding tools and UI. The template includes Kubernetes manifests and Skaffold configuration for local cluster development, making it suitable for teams building complex, multi-step AI agents that need custom generative interfaces.

Prerequisites

  • Python 3.10 or later with uv package manager installed
  • Node.js 18 or later for the Next.js frontend
  • An LLM provider API key (Anthropic, OpenAI, Azure OpenAI, or GitHub Copilot)
  • Docker and kubectl installed if using the Kubernetes development path
  • An MCP-compatible client or LangGraph deployment for the agent backend
1

Clone the Agent Studio Starter repository

Download the bootstrap template to your local machine.

git clone https://github.com/nsphung/agent-studio-starter.git
cd agent-studio-starter
2

Install and start the Python backend

Use uv to install backend dependencies and launch the LangGraph agent server.

cd backend
uv sync
uv run python src/agent/main.py
3

Set environment variables for LLM access

Configure your LLM provider credentials so the LangGraph agent can call the model. The LANGGRAPH_DEPLOYMENT_URL defaults to localhost:8123.

# For Anthropic:
export ANTHROPIC_API_KEY=your_anthropic_api_key_here

# Or for OpenAI:
export OPENAI_API_KEY=your_openai_api_key_here

# Frontend connection (defaults to http://localhost:8123):
export LANGGRAPH_DEPLOYMENT_URL=http://localhost:8123
4

Install and start the Next.js frontend

Install frontend dependencies and launch the CopilotKit UI in development mode.

cd frontend
npm install
npm run dev
5

Add custom tools to the agent

Extend the starter by defining new tool functions in the backend utils module and registering them in the create_deep_agent() call.

# In backend/src/agent/utils.py, define new tools:
def my_custom_tool(param: str) -> str:
    """Tool description here."""
    return f"Result for {param}"

# Then register in create_deep_agent() in main.py
6

Deploy to Kubernetes with Skaffold (optional)

For local cluster development, use Skaffold to build and deploy both services with live reload.

skaffold dev

Agent Studio Starter Examples

Client configuration

Environment configuration for the Agent Studio Starter frontend to connect to the backend LangGraph service.

{
  "mcpServers": {
    "agent-studio": {
      "command": "uv",
      "args": ["run", "python", "src/agent/main.py"],
      "env": {
        "ANTHROPIC_API_KEY": "your_anthropic_api_key_here",
        "LANGGRAPH_DEPLOYMENT_URL": "http://localhost:8123"
      }
    }
  }
}

Prompts to try

Example chat prompts for the default get_weather tool and guidance for extending the agent.

- "What's the weather in San Francisco?"
- "Tell me the weather in Tokyo and London"
- "How's the weather in Berlin right now?"
- "Add a new tool that searches for news articles about a given topic"
- "Show me a generative UI card with the weather for New York"

Troubleshooting Agent Studio Starter

Frontend cannot connect to the backend with 'ECONNREFUSED' error

Ensure the Python backend is running on port 8123 before starting the frontend. Check that LANGGRAPH_DEPLOYMENT_URL matches the actual backend address, especially in Docker or Kubernetes environments where the hostname differs.

uv sync fails with dependency resolution errors

Make sure you are using Python 3.10 or later. Run 'python --version' and 'uv --version' to confirm both are installed. If uv is missing, install it with 'curl -LsSf https://astral.sh/uv/install.sh | sh'.

Skaffold dev fails with 'no kubernetes cluster' error

Skaffold requires a running local Kubernetes cluster such as Docker Desktop's built-in Kubernetes or minikube. Run 'kubectl cluster-info' to confirm a cluster is available before running 'skaffold dev'.

Frequently Asked Questions about Agent Studio Starter

What is Agent Studio Starter?

Agent Studio Starter is a Model Context Protocol (MCP) server that stop building ai agents from scratch. bootstrap starter agent app with langgraph, copilotkit, and beautiful generative uis. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Agent Studio Starter?

Follow the installation instructions on the Agent Studio Starter GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Agent Studio Starter?

Agent Studio Starter works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Agent Studio Starter free to use?

Yes, Agent Studio Starter is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "agent-studio-starter": { "command": "npx", "args": ["-y", "agent-studio-starter"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Agent Studio Starter?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides