mcp-use is the open-source devtools and cloud infrastructure to help dev teams quickly build and deploy custom AI agents with MCP servers. Our SDK has over 5,000 GitHub stars, 100k downloads, and is trusted by engineers at NASA, Cisco, NVIDIA, etc...
mcp-use is serious firepower for dev teams building custom AI agents. Open-source SDK, 5K+ GitHub stars, 100K downloads and trusted by engineers at NASA, Cisco, NVIDIA. Fast deployment, real infrastructure, no fluff.
VibeFlow
Congrats guys! Quick one on observability.. can I see per-tool traces with full request/response and agent decisions, and filter by server or profile?
Morgen
What an incredibly useful library! I've tried it in the context of a small project and have to say this drastically reduced the complexity of managing the code for the agent! Great work @pederzhand @pietrozullo
mcp-use
@david_tedaldi1 Thanks so much! 🙏
That’s exactly what we hoped for: making it easier to build without wrestling with complexity.
Would love to hear more about any ideas for what we should add next!
I’ve used mcp-use myself and it's smooth, straightforward, and gets the job done. Perfect for using MCPs beyond IDEs.
mcp-use
@tatia_tsmindashvili thanks for sharing your experience using it! Indeed, you can build MCP Agents in 6 lines of code!
Toolhouse
lfg!!
mcp-use
@orliesaurus award-winning gif!
Requiring everyone to handle MCPs one at a time is slow, error-prone, and risky. I'm a big fan of mcp-use approach of giving teams a gateway to secure and automate how they use private and 3rd party MCPs. Good luck!
mcp-use
@rberrelleza thanks! If you need any help with MCP we are here!
mcp-use is a standout addition to the AI infrastructure scene, launching today with a clear mission to empower dev teams! As an open-source SDK and infrastructure for MCP servers & agents, it’s filling a crucial gap for those looking to build and deploy custom AI agents quickly.