Happy slice of mcp pizzaMCP.pizza

Agent-MCP

MCP.Pizza Chef: rinadelph

Agent-MCP runs a shared workspace where a team of AI coding assistants each take a slice of the same project, while a common memory bank holds decisions, requirements, and progress so nothing is forgotten between sessions. A live dashboard shows who is working on what. It plugs into Claude Desktop, Cursor, VS Code, and Cline. The authors say plainly that it is built for experienced developers: you clone the repository, install Python and Node, and supply your own OpenAI key.

Coding

Use This MCP server To

Split a big feature into tasks for several assistants Keep project decisions in one place across many sessions See at a glance which assistant is doing what Ask what we decided about a design choice weeks ago Stop two assistants from editing the same files

README

Agent-MCP

Ask DeepWiki

🚀 Advanced Tool Notice: This framework is designed for experienced AI developers who need sophisticated multi-agent orchestration capabilities. Agent-MCP requires familiarity with AI coding workflows, MCP protocols, and distributed systems concepts. We're actively working to improve documentation and ease of use. If you're new to AI-assisted development, consider starting with simpler tools and returning when you need advanced multi-agent capabilities.

💬 Join the Community: Connect with us on Discord to get help, share experiences, and collaborate with other developers building multi-agent systems.

Multi-Agent Collaboration Protocol for coordinated AI software development.

Agent Network Visualization

Think Obsidian for your AI agents - a living knowledge graph where multiple AI agents collaborate through shared context, intelligent task management, and real-time visualization. Watch your codebase evolve as specialized agents work in parallel, never losing context or stepping on each other's work.

Why Multiple Agents?

Beyond the philosophical issues, traditional AI coding assistants hit practical limitations:

  • Context windows overflow on large codebases
  • Knowledge gets lost between conversations
  • Single-threaded execution creates bottlenecks
  • No specialization - one agent tries to do everything
  • Constant rework from lost context and confusion

The Multi-Agent Solution

Agent-MCP transforms AI development from a single assistant to a coordinated team:

Multi-Agent Collaboration Network

Real-time visualization shows your AI team at work - purple nodes represent context entries, blue nodes are agents, and connections show active collaborations. It's like having a mission control center for your development team.

Core Capabilities

Parallel Execution
Multiple specialized agents work simultaneously on different parts of your codebase. Backend agents handle APIs while frontend agents build UI components, all coordinated through shared memory.

Persistent Knowledge Graph

Memory Bank Interface

Your project's entire context lives in a searchable, persistent memory bank. Agents query this shared knowledge to understand requirements, architectural decisions, and implementation details. Nothing gets lost between sessions.

Intelligent Task Management

Agent-MCP FAQ

Which apps does this work with?
Claude Desktop, Cursor, VS Code, and Cline can all connect once it is running on your machine.
Do I need a paid account key?
Yes. You add your own OpenAI key to a settings file before starting it, and the agents run on your OpenAI credit.
How hard is setup?
Hard. The authors describe it as an advanced tool: you clone the repository and need Python 3.10 or newer plus Node 18 or newer.
Can I use this to run several assistants on one project at the same time?
Yes, that is exactly what it is for. Shared memory keeps them from duplicating or undoing each other's work.
Where does the shared memory live?
In your project folder on your own machine, though the assistants themselves still send their work out to OpenAI.
Is there anything to look at besides the chat?
Yes. A separate dashboard you start yourself shows agents, tasks, and the stored project knowledge as a live map.