LangGraph Starter Kit

v1.0.0Coding Agentsstable

Production-ready multi-agent starter kit for LangGraph — 7 patterns, 5 LLM providers, CLI scaffolder, MCP integration, and HTTP server with SSE streaming.

ai-agentsanthropiclangchainlanggraphmcp
Share:
8
Stars
0
Downloads
0
Weekly
0/5

What is LangGraph Starter Kit?

LangGraph Starter Kit is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to production-ready multi-agent starter kit for langgraph — 7 patterns, 5 llm providers, cli scaffolder, mcp integration, and http server with sse streaming.

Production-ready multi-agent starter kit for LangGraph — 7 patterns, 5 LLM providers, CLI scaffolder, MCP integration, and HTTP server with SSE streaming.

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

Features

  • Production-ready multi-agent starter kit for LangGraph — 7 p

Use Cases

Build multi-agent systems with LangGraph and MCP integration.
Use production-ready patterns across 5 LLM providers.
ac12644

Maintainer

LicenseApache-2.0
Languagetypescript
Versionv1.0.0
UpdatedMay 8, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx langgraph-starter-kit

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 LangGraph Starter Kit

The LangGraph Starter Kit is a production-ready multi-agent scaffold supporting 7 agent patterns (Supervisor, Swarm, Human-in-the-Loop, Structured Output, Research, RAG, and Customer Support) across 5 LLM providers (OpenAI, Anthropic, Google, Groq, Ollama). It ships with a CLI scaffolder, MCP integration for external tools, an HTTP server with SSE streaming, and optional LangSmith tracing—making it a solid foundation for building real-world AI agent systems.

Prerequisites

  • Node.js 18+ and npm installed
  • API key for at least one LLM provider (ANTHROPIC_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, or GROQ_API_KEY)
  • Git installed for cloning the repository
  • Optional: Docker and Docker Compose for containerized deployment
  • Optional: LangSmith account for tracing and observability
1

Scaffold a new project with the CLI

The fastest way to start is the interactive CLI scaffolder, which creates a new project directory with your chosen agent pattern and LLM provider already configured.

npx create-langgraph-app
2

Or clone the full starter kit

For access to all 7 patterns and examples, clone the full repository and install dependencies.

git clone https://github.com/ac12644/langgraph-starter-kit.git
cd langgraph-starter-kit
npm install
3

Configure environment variables

Copy the example environment file and set your LLM provider and API keys. Set LLM_PROVIDER to your preferred backend and supply the corresponding API key.

cp .env.example .env

# Example .env contents:
LLM_PROVIDER=anthropic
ANTHROPIC_API_KEY=sk-ant-...
# Optional tracing
LANGCHAIN_TRACING_V2=true
LANGSMITH_API_KEY=ls_...
LANGSMITH_PROJECT=langgraph-starter-kit
# Optional MCP tool servers
MCP_SERVERS_PATH=./mcp-servers.json
4

Run the HTTP server or CLI demo

Start the HTTP server with SSE streaming to expose agent endpoints, or run the CLI demo to interact directly in your terminal.

# HTTP server (port 3000)
npm run dev:http

# CLI demo
npm run dev
5

Invoke an agent via HTTP

Once the server is running, send POST requests to any of the agent pattern endpoints. Each pattern has /invoke and /stream variants.

curl -X POST http://localhost:3000/supervisor/invoke \
  -H "Content-Type: application/json" \
  -d '{"messages": [{"role": "user", "content": "What is the capital of France?"}]}'
6

Configure Claude Desktop to use the MCP server

Add the LangGraph Starter Kit to your Claude Desktop config to expose its agent tools directly to Claude. Run via npx for convenience.

{
  "mcpServers": {
    "langgraph-starter-kit": {
      "command": "npx",
      "args": ["langgraph-starter-kit"]
    }
  }
}

LangGraph Starter Kit Examples

Client configuration

Claude Desktop configuration to run the LangGraph Starter Kit MCP server.

{
  "mcpServers": {
    "langgraph-starter-kit": {
      "command": "npx",
      "args": ["langgraph-starter-kit"]
    }
  }
}

Prompts to try

Use these prompts once Claude is connected to the LangGraph agent server.

- "Use the supervisor agent to research the latest trends in AI agents and summarize findings"
- "Run the RAG agent to answer questions based on my uploaded documents"
- "Demonstrate human-in-the-loop approval by planning a task and asking for my confirmation before proceeding"
- "Use the structured output agent to extract key fields from this JSON response"

Troubleshooting LangGraph Starter Kit

LLM provider errors or authentication failures on startup

Verify that the LLM_PROVIDER value in .env exactly matches one of: anthropic, openai, google, groq, or ollama. Confirm the corresponding API key is set and valid. For Ollama, ensure the Ollama service is running locally on port 11434.

HTTP server starts but agent endpoints return 404

Confirm you started the server with 'npm run dev:http' (not 'npm run dev', which is the CLI mode). The HTTP server runs on port 3000; check that nothing else is bound to that port with 'lsof -i :3000'.

MCP tools not appearing when MCP_SERVERS_PATH is set

Ensure the mcp-servers.json file referenced by MCP_SERVERS_PATH exists and uses valid MCP server definitions. Each entry needs a 'command' and 'args' property pointing to a running MCP server binary or npx package.

Frequently Asked Questions about LangGraph Starter Kit

What is LangGraph Starter Kit?

LangGraph Starter Kit is a Model Context Protocol (MCP) server that production-ready multi-agent starter kit for langgraph — 7 patterns, 5 llm providers, cli scaffolder, mcp integration, and http server with sse streaming. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install LangGraph Starter Kit?

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

Which AI clients work with LangGraph Starter Kit?

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

Is LangGraph Starter Kit free to use?

Yes, LangGraph Starter Kit 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": { "langgraph-starter-kit": { "command": "npx", "args": ["-y", "langgraph-starter-kit"] } } }

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

Read the full setup guide →

Ready to use LangGraph Starter Kit?

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