Happy slice of mcp pizzaMCP.pizza
Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AIFire in da houseCheck it out free

mcp-client

MCP.Pizza Chef: CopilotKit

The mcp-client is a modular Model Context Protocol client designed to orchestrate real-time context flow, tool calling, and protocol logic between MCP hosts and servers. It manages structured data and API interactions, enabling LLMs to access and act on their environment seamlessly. This client supports multi-service development with separate frontend and agent components, facilitating debugging and efficient workflow integration for AI-enhanced applications.

Use This MCP client To

Manage context flow between LLMs and external data sources Coordinate tool calls for multi-step reasoning tasks Integrate multiple MCP servers into unified workflows Debug and develop AI agents with separate frontend and backend Enable real-time environment interaction for LLMs Facilitate protocol logic handling in AI-enhanced apps

README

demospreadsheet.1.mp4

Getting Started

Set Up Environment Variables:

touch .env

Add the following inside .env at the root:

LANGSMITH_API_KEY=lsv2_...
OPENAI_API_KEY=sk-...

Next, create another .env file inside the agent folder:

cd agent
touch .env

Add the following inside agent/.env:

OPENAI_API_KEY=sk-...
LANGSMITH_API_KEY=lsv2_...

Set Up Poetry:

Poetry is used for dependency management in the agent service. To install Poetry, run:

pip install poetry

To verify the installation, run:

poetry --version

Development

We recommend running the frontend and agent separately in different terminals to debug errors and logs:

# Terminal 1 - Frontend
pnpm run dev-frontend

# Terminal 2 - Agent
pnpm run dev-agent

Alternatively, you can run both services together with:

pnpm run dev

Then, open http://localhost:3000 in your browser.

Architecture

The codebase is split into two main parts:

  1. /agent folder – A LangGraph agent that connects to MCP servers and calls their tools.
  2. /app folder – A frontend application using CopilotKit for UI and state synchronization.

mcp-client FAQ

How do I set up environment variables for mcp-client?
Create .env files in the root and agent folders with LANGSMITH_API_KEY and OPENAI_API_KEY keys to authenticate services.
What development tools does mcp-client use?
It uses Poetry for dependency management and pnpm for running frontend and agent services.
Can I run the frontend and agent separately?
Yes, running them in separate terminals helps debug errors and logs effectively.
How do I start both frontend and agent together?
Use the command 'pnpm run dev' to run both services simultaneously.
What is the recommended way to debug mcp-client?
Run frontend and agent separately in different terminals to isolate logs and errors.
Does mcp-client support multiple LLM providers?
Yes, it supports OpenAI, Claude, Gemini, and others through standardized protocol logic.
Is mcp-client suitable for building AI agents?
Yes, it orchestrates context and tool interactions essential for AI agent workflows.
How does mcp-client handle protocol logic?
It manages the flow of context and tool calls between MCP hosts and servers to enable real-time reasoning.