Agent-MCP
A multi-agent system framework enabling efficient AI collaboration through the MCP protocol.
- Type
- MCP
- Transport
- http
- Open source
- Yes
- GitHub Stars
- ★ 1.3k
- Source
- mcp-github
- Repository
- github.com/rinadelph/Agent-MCP
Overview
Agent-MCP is a framework for building multi-agent systems, leveraging the Model Context Protocol (MCP) to enable coordination and efficient AI collaboration. Designed for AI application developers who need multiple specialized agents working in parallel, it offers real-time visualization, persistent knowledge graphs, and intelligent task management—ideal for large codebase development. Available implementations include Python and Node.js/TypeScript.
Capabilities
- ▪Parallel execution of multiple agents
- ▪Persistent knowledge graph
- ▪Intelligent task management
- ▪Real-time visualization
Use cases
Setup
git clone https://github.com/rinadelph/Agent-MCP.git; cd Agent-MCP; cp .env.example .env; uv venv; uv install; uv run -m agent_mcp.cli --port 8080 --project-dir path-to-directory
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
Who is Agent-MCP suitable for?
Experienced AI developers, especially those requiring advanced multi-agent orchestration capabilities.
How do I get started with Agent-MCP?
Clone the repository, configure environment variables, install dependencies, and start the server.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.