#766 · Primary category: AI Agents & Automation
mcp-agent
Build effective agents using Model Context Protocol and simple workflow patterns
Project last updated:01/25/26
GitHub Stars
8.5K
Forks
881
Contributors
60
License
Apache-2.0
Why we included this project
Teams shipping their first real LLM-powered agent usually discover that connecting tools is half the work. This framework makes Model Context Protocol the transport, so any MCP-compatible tool server plugs in and the library handles the lifecycle of those connections for you. It also turns the agent patterns Anthropic documented, routing, tool loops, orchestrator-workers, into composable pieces you can chain, which helps when one task actually needs several steps or roles. If you are deciding how to structure a production agent rather than a demo, the examples give you a working reference to build from.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.