Happy slice of mcp pizzaMCP.pizza

tutorials

MCP.Pizza Chef: hollaugo

This collection provides ready-to-run AI agent examples demonstrating how to build intelligent assistants using the Model Context Protocol. You can run these servers to explore different AI workflows, such as investment research, fantasy sports, or task management, primarily within ChatGPT. Setup requires some developer knowledge to install and run the code, but no special prerequisites are needed beyond that.

Other

Use This MCP server To

Run example AI agents inside ChatGPT Explore how to build AI agents with MCP Test investment research agents Try Fantasy Premier League assistant Learn multi-agent communication Experiment with Slack-integrated AI bots Build custom AI workflows

README

AI Agent Tutorials & Implementations

A comprehensive collection of production-ready AI agent implementations showcasing different frameworks, protocols, and integration patterns. This repository demonstrates various approaches to building intelligent agents with Model Context Protocol (MCP), multi-agent systems, and real-world integrations.

Repository Overview

This repository contains multiple agent implementations, each demonstrating different architectural patterns and use cases:

Project Framework Key Features Use Case
agent2agent LangGraph + A2A Protocol Remote agent communication, Slack integration Investment research
mcp-financial FastMCP + FastAPI ASGI integration, CLI client Financial data analysis
bright-mcp-server-overview Dual: LangGraph + ADK Memory persistence, extended timeouts Web scraping & research
fpl-deepagent FastMCP + React UI Streamable HTTP, ChatGPT integration Fantasy Premier League
task-manager-app FastMCP + React UI + Supabase OAuth (Auth0), per-user DB state, Slack notifications Task management in ChatGPT
notion-mcp-agent LangGraph + MCP Notion integration, database management Knowledge management
claude-advanced-tool-use Claude API + FastMCP PTC, Tool Search, MCP integration Token-efficient AI agents
claude-skills Claude Skills API Document generation, custom skills PowerPoint, Excel, Word creation
openai-chatkit-starter-app Next.js + ChatKit Agent Builder integration, web component ChatKit UI development
mastra-overview Mastra framework Multi-LLM orchestration Framework exploration
smithery-example Smithery + FastMCP MCP playground, development tools MCP development
mcp-apps MCP Apps (OpenAI Apps SDK) Example MCP Apps (weather + stock analysis) MCP Apps reference implementations

Project Descriptions

agent2agent/

Investment Research Analyst Agent

A production-ready investment research agent implementing Google's Agent-to-Agent (A2A) protocol for remote agent communication.

Key Features:

  • Framework: LangGraph with LangChain
  • Protocol: Agent-to-Agent (A2A) for remote communication
  • Integration: Slack with Block Kit UI and metadata modals
  • Architecture: FastAPI server exposing both A2A endpoints and Slack events
  • Memory: Persistent conversation state management
  • Deployment: Docker ready with Render.com configuration

Technical Stack:

  • LangGraph for agent orchestration
  • FastAPI for A2A protocol implementation
  • Slack Block Kit for interactive UI
  • LangSmith for observability (optional)
  • Docker for containerized deployment

Use Cases:

  • Stock summaries and analysis
  • SEC filings research
  • Analyst recommendations
  • Financial data aggregation
  • Investment research workflows

tutorials FAQ

Can I use this to run AI agents with ChatGPT?
Yes — this server hosts various AI agent tutorials and implementations designed to work with ChatGPT and other clients.
Do I need an API key or account to use these tutorials?
Typically, yes — some tutorials may require API keys for OpenAI, Claude, or Gemini models depending on the agent.
Is it easy to set up these tutorials?
No — setup generally requires developer skills like installing packages and running servers.
Which apps work with these tutorials?
They are designed primarily for ChatGPT but can integrate with other MCP-compatible clients.
How do I install the tutorials?
You install them using developer tools like pip or smithery, not just one-click installs.