A2A LangGraph Boilerplate
a boilerplate for developers who want to start building an AI agent cluster with A2A and MCP servers integration faster and more efficiently.
What is A2A LangGraph Boilerplate?
A2A LangGraph Boilerplate is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to boilerplate for developers who want to start building an ai agent cluster with a2a and mcp servers integration faster and more efficiently.
a boilerplate for developers who want to start building an AI agent cluster with A2A and MCP servers integration faster and more efficiently.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- a boilerplate for developers who want to start building an A
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx a2a-langgraph-boilerplateConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use A2A LangGraph Boilerplate
A2A LangGraph Boilerplate is a developer-focused starter project for building multi-agent AI systems that combine Google's Agent-to-Agent (A2A) protocol with LangGraph orchestration and MCP server tool integration. It provides a FastAPI application with pre-wired supervisor-worker agent patterns, a PostgreSQL-backed task store, MCP server management, and Swagger API documentation — giving teams a production-ready scaffold to extend rather than building agent infrastructure from scratch. It is ideal for developers prototyping autonomous agent clusters that need structured tool access and inter-agent communication.
Prerequisites
- Python 3.10 or later with pip
- PostgreSQL database (local or remote) with a connection string ready
- Node.js (for MCP server subprocesses if integrating npm-based MCP tools)
- An MCP-compatible client or API consumer to interact with the deployed agents
Clone the repository
Start by cloning the boilerplate repository to your local machine.
git clone https://github.com/mrgoonie/a2a-langgraph-boilerplate.git
cd a2a-langgraph-boilerplateInstall Python dependencies
Install all required packages from the requirements file.
pip install -r requirements.txtConfigure environment variables
Copy the example env file and set your PostgreSQL connection string along with any LLM API keys needed by your agents.
cp .env.example .env
# Edit .env and set:
# DATABASE_URL=postgresql://user:password@localhost:5432/a2a_dbStart the application
Launch the FastAPI server with uvicorn. The API will be available at http://127.0.0.1:8000 with Swagger docs at /docs.
uvicorn app.main:app --reloadRun the demo workflow
Test the boilerplate with the included simple demo that exercises the supervisor-worker agent pattern end to end.
python -m tests.test_ai_crew_simple_demoIntegrate with an MCP client
Once the server is running, add it as an MCP server in your client config pointing to the local FastAPI endpoint.
{
"mcpServers": {
"a2a-langgraph-boilerplate": {
"command": "python",
"args": ["-m", "uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"],
"cwd": "/path/to/a2a-langgraph-boilerplate",
"env": {
"DATABASE_URL": "postgresql://user:pass@localhost:5432/a2a_db"
}
}
}
}A2A LangGraph Boilerplate Examples
Client configuration
MCP config entry for the A2A LangGraph boilerplate running as a local Python service.
{
"mcpServers": {
"a2a-langgraph-boilerplate": {
"command": "python",
"args": ["-m", "uvicorn", "app.main:app", "--host", "127.0.0.1", "--port", "8000"],
"cwd": "/path/to/a2a-langgraph-boilerplate",
"env": {
"DATABASE_URL": "postgresql://user:password@localhost:5432/a2a_db"
}
}
}
}Prompts to try
Example instructions for working with the A2A agent crew system.
- "Create a new AI crew with a supervisor agent and two worker agents: one for research and one for writing."
- "Add a web search MCP tool to the research agent."
- "Start a task: research the latest LangGraph releases and produce a summary."
- "Show me the activity logs for the last crew run."
- "List all configured MCP servers and their connection status."Troubleshooting A2A LangGraph Boilerplate
Application fails to start with 'could not connect to database' error
Verify the DATABASE_URL in your .env file is correct and that the PostgreSQL server is running and accessible. Test the connection with 'psql $DATABASE_URL' before starting the app.
Agents are not calling MCP tools
Ensure the MCP servers are registered in the application's tool configuration and that each MCP server process is running. Check the /docs Swagger UI to verify tool endpoints are registered and accessible.
Demo test script exits immediately with no output
Run 'python -m pytest tests/ -v' instead to see detailed output. Check that all environment variables are set and that the FastAPI server is already running before executing the demo script.
Frequently Asked Questions about A2A LangGraph Boilerplate
What is A2A LangGraph Boilerplate?
A2A LangGraph Boilerplate is a Model Context Protocol (MCP) server that boilerplate for developers who want to start building an ai agent cluster with a2a and mcp servers integration faster and more efficiently. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install A2A LangGraph Boilerplate?
Follow the installation instructions on the A2A LangGraph Boilerplate GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with A2A LangGraph Boilerplate?
A2A LangGraph Boilerplate works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is A2A LangGraph Boilerplate free to use?
Yes, A2A LangGraph Boilerplate is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
A2A LangGraph Boilerplate Alternatives — Similar Coding Agents Servers
Looking for alternatives to A2A LangGraph Boilerplate? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
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.
Set Up A2A LangGraph Boilerplate in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use A2A LangGraph Boilerplate?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.